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. 6868
    Prev
    Next
    INDEX
    Explanations

    references to personal or organizational achievements and transitions

    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
    majánló
    -1.11
    sizeCache
    -1.10
    Datuak
    -1.08
    <unused43>
    -1.07
    <unused23>
    -1.06
    <unused16>
    -1.06
    <unused41>
    -1.06
    <unused42>
    -1.06
    [@BOS@]
    -1.05
    <unused3>
    -1.05
    POSITIVE LOGITS
     
    0.40
    ↵
    0.38
    ,
    0.38
    ↵↵
    0.37
     endeavor
    0.36
    又
    0.36
     cultural
    0.35
    .
    0.35
     personal
    0.34
     pursuits
    0.34
    Activations Density 0.842%

    No Known Activations