© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14287
    Prev
    Next
    INDEX
    Explanations

    sections of a document related to analytical evaluations and assessments

    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
    Билгалдахарш
    -0.73
     linkovi
    -0.69
    tagHelperRunner
    -0.67
     GoogleFonts
    -0.66
     surla
    -0.66
    SharedDtor
    -0.65
    httphttps
    -0.61
     kaarangay
    -0.60
     فريبيس
    -0.58
    fromnode
    -0.58
    POSITIVE LOGITS
     paralysis
    0.51
     tools
    0.43
    ila
    0.34
    al
    0.34
    JSONException
    0.33
    bericht
    0.33
    ator
    0.33
     проводится
    0.33
    ar
    0.32
    ysis
    0.32
    Activations Density 0.146%

    No Known Activations