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. 25-GEMMASCOPE-RES-16K
    6. 12418
    Prev
    Next
    INDEX
    Explanations

    elements related to configuration and initialization in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '}>
    -0.71
    UnusedPrivate
    -0.67
    awtextra
    -0.66
    parsedMessage
    -0.64
    ;}
    -0.63
    Autoritní
    -0.63
     igång
    -0.60
    OGND
    -0.60
    //}
    -0.59
    LookAnd
    -0.59
    POSITIVE LOGITS
    end
    1.01
     end
    0.94
    End
    0.61
    rescue
    0.59
    nend
    0.57
    endt
    0.57
     End
    0.55
     END
    0.55
     rescue
    0.53
    =
    0.52
    Activations Density 0.102%

    No Known Activations