© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105761
    Prev
    Next
    INDEX
    Explanations

    expressions of identity and self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Forms of the verb "to be" (am, is, are, be, being) used to express identity, classification, or state of existence in various contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.63
    FormTagHelper
    -0.62
    Rüyada
    -0.57
     Normdatei
    -0.56
     useCallback
    -0.54
    Neat
    -0.54
     CFS
    -0.54
    meneu
    -0.54
    ⓧ
    -0.53
    addCriterion
    -0.53
    POSITIVE LOGITS
    NotBe
    0.33
    󠁣
    0.32
     a
    0.30
    toBe
    0.30
    Kjelder
    0.29
    ^{*}=
    0.29
    ()==
    0.28
    </tr>
    0.28
     super
    0.28
    पया
    0.28
    Activations Density 0.058%

    No Known Activations