© 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. 960
    Prev
    Next
    INDEX
    Explanations

    references to data and statistics

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

    "Examples" or similar words

    np_acts-logits-general · gemini-2.0-flash

    examples

    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
    AddTagHelper
    -0.79
    HtmlAttribute
    -0.57
    ########.
    -0.55
    IntoConstraints
    -0.54
     Efq
    -0.53
     ModelExpression
    -0.53
    Erreferentziak
    -0.52
     CURIAM
    -0.51
     ogóle
    -0.50
    ViewSet
    -0.50
    POSITIVE LOGITS
     examples
    1.54
     Examples
    1.49
    Examples
    1.42
    examples
    1.29
     exemples
    1.24
    主な
    1.19
     some
    1.18
     among
    1.18
     Beispiele
    1.15
     exemplos
    1.13
    Activations Density 0.286%

    No Known Activations