© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12579
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations related to fields and constants in advanced theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.66
    ')))
    -0.59
     Guen
    -0.59
    ůměr
    -0.58
     ouvertes
    -0.56
    )});
    -0.54
    '))
    
    -0.54
    ATIVA
    -0.54
    ))->
    -0.53
     Boas
    -0.53
    POSITIVE LOGITS
    }}{
    0.97
    )}{
    0.96
    enumi
    0.94
    }{
    0.92
    _{
    0.89
    }{\
    0.86
    |}{
    0.86
    InjectAttribute
    0.85
    ={`/
    0.83
     Reverso
    0.83
    Activations Density 0.287%

    No Known Activations