© 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. 9-GEMMASCOPE-RES-131K
    11. 121208
    Prev
    Next
    INDEX
    Explanations

    names of people and their associations in various contexts

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

    2-part suffixes (e.g., -ri, -ru, -rein)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.90
    IntoConstraints
    -0.84
    NameInMap
    -0.82
     EconPapers
    -0.79
     للمعارف
    -0.77
    MigrationBuilder
    -0.75
     OFDb
    -0.73
     lenker
    -0.73
     indígen
    -0.72
     increí
    -0.72
    POSITIVE LOGITS
     mut
    0.28
    ARGV
    0.26
     му
    0.25
     just
    0.25
     otro
    0.24
     Familienname
    0.24
     شم
    0.23
     later
    0.23
     sp
    0.22
     rowspan
    0.22
    Activations Density 0.240%

    No Known Activations