© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7117
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords related to conditional statements and object instantiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gry
    -0.41
    hake
    -0.41
    asteroide
    -0.40
     CGSize
    -0.40
     Requis
    -0.40
    ❸
    -0.38
    citep
    -0.38
    clou
    -0.38
     gyhoeddwyd
    -0.38
    Denn
    -0.37
    POSITIVE LOGITS
    //
    0.60
    ußt
    0.51
     مشين
    0.50
    存于互联网档案馆
    0.47
    なし
    0.46
    VYMaps
    0.44
    /*
    0.43
    BASEPATH
    0.43
    stateProvider
    0.43
    uxxxx
    0.43
    Activations Density 0.158%

    No Known Activations