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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7194
    Prev
    Next
    INDEX
    Explanations

    terms and references related to academic scheduling and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.70
    awtextra
    -0.68
    setViewportView
    -0.61
    帖最后由
    -0.57
     doInBackground
    -0.57
    ReusableCell
    -0.57
     surla
    -0.56
    VIAF
    -0.55
    ioutil
    -0.55
    SharedCtor
    -0.54
    POSITIVE LOGITS
     semester
    1.08
     semesters
    0.88
     Semester
    0.86
     term
    0.84
    semester
    0.81
    Semester
    0.78
     Term
    0.77
    Term
    0.76
     ترم
    0.73
     sem
    0.72
    Activations Density 0.182%

    No Known Activations