© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10629
    Prev
    Next
    INDEX
    Explanations

    code constructs related to error handling and device management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or macro definitions with bit shifting

    np_acts-logits-general · gemini-2.0-flash

    technical and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.82
    ]}>
    -0.65
    jspb
    -0.64
    ]=="
    -0.61
    stateProvider
    -0.60
    ]]]
    -0.60
    elseif
    -0.59
     }],
    -0.59
     Div
    -0.58
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
    ->
    0.63
     jurídico
    0.58
     clínico
    0.58
     Оно
    0.58
     RSSSF
    0.56
     Constitucional
    0.56
     Assyrian
    0.56
     vetorial
    0.56
     abstrato
    0.55
    seamnă
    0.53
    Activations Density 0.404%

    No Known Activations