© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1905
    Prev
    Next
    INDEX
    Explanations

    numeric values and other data related to measurements

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

    Informal greetings and conversational words

    np_acts-logits-general · gemini-2.0-flash

    obviously done

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     kaarangay
    -0.98
     незавершена
    -0.98
     GenerationType
    -0.97
     AttributeSet
    -0.93
     ModelExpression
    -0.91
    تقاوى
    -0.91
    fillType
    -0.88
    جغرافيا
    -0.88
    醐
    -0.87
     كومونز
    -0.85
    POSITIVE LOGITS
    Hello
    0.78
    Hey
    0.75
    Hi
    0.74
    Wow
    0.73
    I
    0.73
     Hello
    0.72
    What
    0.69
    The
    0.65
    We
    0.64
    This
    0.63
    Activations Density 0.386%

    No Known Activations