Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2199
    Prev
    Next
    INDEX
    Explanations

    concepts related to social conditioning and systemic issues of oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proportionate
    -0.47
     HasFactory
    -0.45
     muligt
    -0.43
     qualif
    -0.41
    ༘
    -0.41
     dépla
    -0.40
     fört
    -0.40
     Irregular
    -0.40
     intent
    -0.40
     qualified
    -0.40
    POSITIVE LOGITS
    IsMutable
    0.47
    detectChanges
    0.45
    DIPSETTING
    0.45
    kloped
    0.44
    ondissement
    0.44
    новништво
    0.43
     hegemony
    0.41
     dikt
    0.40
     assumptions
    0.40
     rut
    0.39
    Activations Density 0.610%

    No Known Activations