© 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. 2-GEMMASCOPE-RES-16K
    11. 4059
    Prev
    Next
    INDEX
    Explanations

    modal verbs and auxiliary verbs indicating actions, obligations, or possibilities

    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
     ModelExpression
    -0.74
    UnusedPrivate
    -0.74
    ThroughAttribute
    -0.73
    principalTable
    -0.69
     learnt
    -0.67
    SequentialGroup
    -0.66
    UseVisualStyle
    -0.65
    "]);
    -0.65
    StoryboardSegue
    -0.62
    SourceChecksum
    -0.61
    POSITIVE LOGITS
    rófono
    0.56
    ttino
    0.55
    IsUnicode
    0.48
    ocardial
    0.47
    ificantly
    0.47
    țiune
    0.46
    Spoiler
    0.45
     Tarzan
    0.45
    <bos>
    0.45
    CDATA
    0.45
    Activations Density 0.805%

    No Known Activations