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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13346
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to military personnel and tax obligations

    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
    IntoConstraints
    -0.45
    SharedCtor
    -0.41
    nement
    -0.40
     ModelExpression
    -0.37
    makeConstraints
    -0.36
    EDEFAULT
    -0.36
    findpost
    -0.34
    TagMode
    -0.34
     للاسماء
    -0.34
    ModelForm
    -0.33
    POSITIVE LOGITS
     return
    3.97
     returning
    3.44
     Return
    3.42
     returned
    3.38
     returns
    3.31
     RETURN
    3.22
    Return
    3.09
     Returning
    3.06
    return
    2.94
    Returning
    2.88
    Activations Density 3.317%

    No Known Activations