© 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. 15-GEMMASCOPE-RES-16K
    11. 1547
    Prev
    Next
    INDEX
    Explanations

    technical and specialized vocabulary related to equipment and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dataclass
    -0.46
     @"/
    -0.44
    ConstraintMaker
    -0.43
     ocasião
    -0.40
    注入
    -0.37
    WithFormat
    -0.36
    إن
    -0.36
     apostle
    -0.35
    MethodImpl
    -0.35
    Vezi
    -0.35
    POSITIVE LOGITS
     footage
    0.80
     equipment
    0.68
     circuitry
    0.66
     matériel
    0.66
     legislation
    0.65
    Legislation
    0.65
    legislation
    0.63
    equipment
    0.63
    poetry
    0.63
     zboží
    0.62
    Activations Density 2.198%

    No Known Activations