© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39271
    Prev
    Next
    INDEX
    Explanations

    references to characters and their relationships in narratives

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

    pronouns: he, him, his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    GEBURTSDATUM
    -0.47
     विश्वसनीयता
    -0.47
    HideFlags
    -0.46
    SourceChecksum
    -0.46
     Decimal
    -0.46
    Diwedd
    -0.45
    knit
    -0.45
    zzati
    -0.44
    béco
    -0.43
    rubin
    -0.43
    POSITIVE LOGITS
    empuan
    0.42
     Geschle
    0.42
     незавершена
    0.42
    对她
    0.39
     kanya
    0.39
     sexe
    0.38
     sesso
    0.36
     her
    0.36
     she
    0.36
    给她
    0.35
    Activations Density 0.107%

    No Known Activations