© 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. 38-GEMMASCOPE-RES-16K
    11. 8182
    Prev
    Next
    INDEX
    Explanations

    formatting tags and emphasis indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.55
    SequentialGroup
    -0.53
    Hochspringen
    -0.49
     actionPerformed
    -0.48
     ProtoMessage
    -0.46
     AssemblyCompany
    -0.42
    RTHOOK
    -0.42
     defStyle
    -0.41
    ::_('
    -0.40
     jspb
    -0.39
    POSITIVE LOGITS
    ‘
    1.02
    s
    0.81
    ️
    0.71
    “
    0.69
    <strong>
    0.66
    <em>
    0.65
    “,
    0.62
    nın
    0.62
    “)
    0.61
    ︎
    0.60
    Activations Density 0.278%

    No Known Activations