© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly in various contexts

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

    names of people, particularly in lists or contexts involving achievements or roles.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    出版年
    -0.47
    ichel
    -0.42
    forRoot
    -0.41
    rungsseite
    -0.40
    ardon
    -0.40
     CreateTagHelper
    -0.37
    esseract
    -0.37
    leg
    -0.36
     pening
    -0.36
    aren
    -0.36
    POSITIVE LOGITS
     etc
    0.69
    Datuak
    0.59
    等等
    0.54
    etc
    0.53
     usw
    0.51
    Etc
    0.50
    */].
    0.50
     others
    0.49
     Etc
    0.47
    protoimpl
    0.47
    Activations Density 0.290%

    No Known Activations