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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11678
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and scientific research involving proteins and health

    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
    ValueStyle
    -0.80
     Coder
    -0.74
     Squad
    -0.72
    ruppen
    -0.71
    lenburg
    -0.71
    Fila
    -0.70
    varphi
    -0.69
    DSC
    -0.68
    codegen
    -0.68
     φ
    -0.67
    POSITIVE LOGITS
    Datuak
    0.73
     monaster
    0.71
     '{@
    0.68
    yntaxException
    0.68
     Poincaré
    0.67
    Inet
    0.66
    styleType
    0.66
     Darío
    0.65
     &'
    0.64
     '-')
    0.64
    Activations Density 2.003%

    No Known Activations