© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1550
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or excerpts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences or paragraphs that start with the phrase "Here's".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    deictic introductory statements that point the reader to forthcoming content (e.g., “here …” constructions introducing examples, excerpts, lists, or code).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the phrase "Here's" or "Here is" at the beginning of a sentence or statement.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.73
     pihaknya
    -0.57
     useAuth
    -0.56
     CommandType
    -0.56
     pymysql
    -0.55
    endphp
    -0.54
     démocr
    -0.52
     policiales
    -0.52
    phazard
    -0.52
     للاسماء
    -0.52
    POSITIVE LOGITS
     Voici
    0.58
    Voici
    0.54
    voici
    0.54
    Here
    0.52
     Here
    0.52
     voici
    0.47
     list
    0.46
     Вот
    0.46
     proof
    0.45
     HERE
    0.45
    Activations Density 0.068%

    No Known Activations