© 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. 25-GEMMASCOPE-RES-16K
    11. 263
    Prev
    Next
    INDEX
    Explanations

    conversational cues and references indicating personal connections and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.82
    DockStyle
    -0.65
     snippetHide
    -0.64
    BagConstraints
    -0.64
     MainAxisSize
    -0.60
    UnusedPrivate
    -0.59
    OGND
    -0.59
    jsii
    -0.58
    TintMode
    -0.58
    EDEFAULT
    -0.57
    POSITIVE LOGITS
     return
    3.71
     Return
    3.21
     returned
    3.18
     returns
    3.09
     returning
    3.03
    Return
    2.98
     RETURN
    2.96
    return
    2.87
     Returning
    2.70
     Returns
    2.58
    Activations Density 0.643%

    No Known Activations