© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21266
    Prev
    Next
    INDEX
    Explanations

    pronouns and expressions of personal connection or involvement

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

    pronoun + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.43
    obenz
    -0.42
     roadways
    -0.41
    úblico
    -0.41
     folks
    -0.40
    ennifer
    -0.40
     awhile
    -0.40
    gameId
    -0.39
     einst
    -0.39
    ständige
    -0.39
    POSITIVE LOGITS
     Nowadays
    0.65
     nowadays
    0.64
     Moreover
    0.59
    Moreover
    0.58
    Nowadays
    0.58
     shrimps
    0.56
     quitted
    0.55
     exercices
    0.55
     indeed
    0.53
     ressources
    0.51
    Activations Density 0.146%

    No Known Activations