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. 9-GEMMASCOPE-RES-16K
    6. 11206
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and expectations related to functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fully
    -0.36
    //
    -0.33
    @
    -0.33
    onshire
    -0.32
     stake
    -0.32
     Hills
    -0.31
     dragen
    -0.31
     stadio
    -0.30
     HILLS
    -0.29
    ia
    -0.29
    POSITIVE LOGITS
    WireFormatLite
    0.60
    tableFuture
    0.58
    @[+][
    0.57
     Chwiliwch
    0.52
    RegressionTest
    0.52
    posedge
    0.52
    发表于
    0.50
    
    0.50
    principalColumn
    0.50
    SharedCtor
    0.50
    Activations Density 0.714%

    No Known Activations