© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9028
    Prev
    Next
    INDEX
    Explanations

    negations and specific forms of the verb "to be"

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

    the copula verb "is" and negation markers like "not".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     retardation
    -0.40
     migrantes
    -0.38
     inscripción
    -0.38
    ènements
    -0.37
     Kette
    -0.36
     ciudadanía
    -0.36
     récord
    -0.36
     Derechos
    -0.36
     Defensa
    -0.35
     kule
    -0.35
    POSITIVE LOGITS
    PropertyChanging
    0.59
     snippetHide
    0.58
    elemField
    0.58
     nahilalakip
    0.58
    principalColumn
    0.57
    Derbyniad
    0.54
    KURZBESCHREIBUNG
    0.53
    AsUp
    0.53
    Хьажоргаш
    0.52
     very
    0.52
    Activations Density 0.122%

    No Known Activations