© 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. 18-GEMMASCOPE-RES-16K
    11. 8449
    Prev
    Next
    INDEX
    Explanations

    closing and ending braces, parentheses, and semicolons typically used in programming syntax

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

    Code blocks and code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Otherwise
    -1.07
     otherwise
    -1.06
    Otherwise
    -1.01
     ELSE
    -0.99
     Else
    -0.99
     else
    -0.96
    ELSE
    -0.94
     altrimenti
    -0.93
    otherwise
    -0.89
    Else
    -0.87
    POSITIVE LOGITS
    InputBorder
    0.62
    RenderAtEndOf
    0.47
     Schwert
    0.45
    Fully
    0.45
    fully
    0.43
    ichtig
    0.43
    gebir
    0.42
     indisponible
    0.42
    ends
    0.42
     Grosvenor
    0.42
    Activations Density 0.045%

    No Known Activations