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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10863
    Prev
    Next
    INDEX
    Explanations

    function calls that produce output or request input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    protoimpl
    -0.73
     invokingState
    -0.72
    댑
    -0.70
    yenne
    -0.70
    Démographie
    -0.69
     Amiga
    -0.69
     esters
    -0.69
     bow
    -0.68
    öhne
    -0.67
    mitter
    -0.65
    POSITIVE LOGITS
    println
    1.71
    WriteLine
    1.35
     println
    1.22
    AppendLine
    0.97
    )}.
    0.76
     Klin
    0.72
    "]="
    0.67
    ."]
    0.67
    writerow
    0.66
    "]=
    0.65
    Activations Density 0.029%

    No Known Activations