Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14058
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or interaction in the comments section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InvalidProtocol
    -0.63
    طلحات
    -0.61
    Edm
    -0.61
    selaer
    -0.60
    MigrationBuilder
    -0.59
     Protobuf
    -0.57
    INCREF
    -0.56
    interopRequire
    -0.56
    بوابة
    -0.55
    PREFERRED
    -0.54
    POSITIVE LOGITS
     comment
    3.24
     comments
    2.93
    comment
    2.90
     Comment
    2.88
    Comment
    2.79
     commenting
    2.64
     COMMENT
    2.58
     Comments
    2.52
    comments
    2.52
    Comments
    2.45
    Activations Density 0.191%

    No Known Activations