© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15672
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and biological entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hedges
    -0.69
     Wilber
    -0.69
    ANTIC
    -0.66
    Timber
    -0.65
    Authenticator
    -0.64
     Pra
    -0.64
     rú
    -0.63
     Wanna
    -0.63
     Timberlake
    -0.63
    <h1>
    -0.63
    POSITIVE LOGITS
    MigrationBuilder
    1.07
     unknownFields
    0.97
    StructEnd
    0.94
     препратки
    0.92
    complexContent
    0.92
    
    0.88
    migrationBuilder
    0.87
    ]")]
    0.86
    EDEFAULT
    0.86
    upol
    0.86
    Activations Density 9.913%

    No Known Activations