© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8118
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to "taking" or similar terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worked
    -0.46
     der
    -0.45
     aber
    -0.44
     in
    -0.42
    dzić
    -0.41
     ne
    -0.41
    ↵
    -0.41
    腔
    -0.40
     th
    -0.40
     t
    -0.40
    POSITIVE LOGITS
     Roskov
    1.19
    zzleHttp
    0.97
     оригіналу
    0.97
    InjectAttribute
    0.95
    IsMutable
    0.94
     propOrder
    0.92
    MigrationBuilder
    0.92
    MLLoader
    0.92
    RectangleBorder
    0.92
    ⓧ
    0.91
    Activations Density 0.344%

    No Known Activations