© 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. 12-GEMMASCOPE-RES-16K
    6. 8459
    Prev
    Next
    INDEX
    Explanations

    HTML span elements with specific classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.88
     Horace
    -0.88
     Mühl
    -0.87
     propOrder
    -0.81
    ()?;
    -0.80
    findpost
    -0.80
    Horace
    -0.80
     resourceCulture
    -0.78
    MemoryWarning
    -0.76
     Herrick
    -0.76
    POSITIVE LOGITS
    span
    1.93
     span
    1.45
     SPAN
    1.41
    SPAN
    1.38
    spans
    1.38
     Span
    1.35
    Span
    1.35
     spans
    1.15
    MessageTagHelper
    1.09
     spanned
    0.91
    Activations Density 0.041%

    No Known Activations