© 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. 7-GEMMASCOPE-RES-16K
    11. 12030
    Prev
    Next
    INDEX
    Explanations

    references to grants, funding, and conflicts of interest in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.58
    AllAfrica
    -0.56
     Presidencia
    -0.48
    Scénario
    -0.48
     virtually
    -0.47
    IsMutable
    -0.46
     Lég
    -0.46
    </caption>
    -0.45
    uticos
    -0.45
     rarement
    -0.45
    POSITIVE LOGITS
     anymore
    1.15
     nor
    0.96
     any
    0.81
     melainkan
    0.78
     quelconque
    0.73
     necessarily
    0.68
     אלא
    0.67
    InvalidProtocol
    0.65
     or
    0.65
    有任何
    0.65
    Activations Density 2.276%

    No Known Activations