© 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. 8-GEMMASCOPE-RES-16K
    6. 1674
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements, specifically related to programming logic and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewStyle
    -0.79
     Probl
    -0.74
     Houſe
    -0.73
     Reſ
    -0.72
    Probl
    -0.72
     Diſ
    -0.71
     ſeveral
    -0.69
    abestanden
    -0.69
     piede
    -0.68
     individualism
    -0.66
    POSITIVE LOGITS
    __':
    
    1.09
    __':
    0.98
    UTERS
    0.88
    __":
    0.87
    __":
    
    0.84
    >):
    0.70
     []:
    0.69
    thenReturn
    0.69
    RTRS
    0.69
    :])
    0.69
    Activations Density 0.051%

    No Known Activations