© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    structural and syntactic elements in programming or data formats

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

    Code snippets with brackets and braces

    np_acts-logits-general · gemini-2.0-flash

    closing code delimiters

    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
    ########.
    -0.78
     pronouncing
    -0.64
     onCancelled
    -0.62
    saraba
    -0.61
    styleType
    -0.57
     circula
    -0.55
     Shaksp
    -0.55
     jsPsych
    -0.53
    BuildContext
    -0.53
     rounding
    -0.52
    POSITIVE LOGITS
    omitempty
    0.69
    </tr>
    0.64
    Viitteet
    0.64
    ".$_
    0.63
     désolés
    0.62
    }.
    0.62
    #
    0.61
     CreateTagHelper
    0.61
    ";
    0.60
    );
    0.58
    Activations Density 0.062%

    No Known Activations