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. 17-GEMMASCOPE-RES-16K
    6. 7119
    Prev
    Next
    INDEX
    Explanations

    terms related to iron and its biochemical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.77
    Попис
    -0.70
    TemporalType
    -0.69
    PyExc
    -0.68
    schild
    -0.67
     AppModule
    -0.67
    zeptember
    -0.66
    DeleteBehavior
    -0.66
    קישורים
    -0.64
     Popp
    -0.64
    POSITIVE LOGITS
     Iron
    0.90
    Iron
    0.82
     iron
    0.80
     IRON
    0.78
    SourceChecksum
    0.73
     بيها
    0.71
     Irons
    0.67
    iron
    0.67
    Fe
    0.62
     irons
    0.60
    Activations Density 0.259%

    No Known Activations