© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27760
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Thank you, I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.79
     TestBed
    -0.76
     Вікі
    -0.75
    ,:);
    -0.74
    AnimationsModule
    -0.73
     betweenstory
    -0.73
    IsMutable
    -0.73
    Попис
    -0.72
     ſever
    -0.69
    \{\\
    -0.68
    POSITIVE LOGITS
     I
    0.59
     how
    0.52
    how
    0.52
     Did
    0.51
     How
    0.49
     What
    0.48
    ところで
    0.47
    what
    0.46
     what
    0.45
    How
    0.44
    Activations Density 0.021%

    No Known Activations