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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13744
    Prev
    Next
    INDEX
    Explanations

    instances of introductory phrases or transitional phrases that lead into new information or examples

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

    Text following "Here's" or "Here is"

    np_acts-logits-general · gemini-2.0-flash

    here's my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    -0.69
     CommandType
    -0.66
     pymysql
    -0.57
     MutableLiveData
    -0.56
    allowNull
    -0.52
     Discogs
    -0.52
     useAuth
    -0.52
     OnDestroy
    -0.51
    spk
    -0.51
    ValueStyle
    -0.50
    POSITIVE LOGITS
     Voici
    0.53
    Voici
    0.52
    voici
    0.49
    rungsseite
    0.46
     voici
    0.46
     liste
    0.43
     summary
    0.42
    Here
    0.41
     ecco
    0.41
     Here
    0.39
    Activations Density 0.088%

    No Known Activations