© 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. 20-GEMMASCOPE-RES-16K
    6. 6091
    Prev
    Next
    INDEX
    Explanations

    elements of LaTeX document structure and formatting commands

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

    Width or size specification in figures

    np_acts-logits-general · gemini-2.0-flash

    width and dimension specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.58
    //</
    -0.50
    }-*/;
    -0.48
    audiovisuel
    -0.47
    typeparam
    -0.47
    ResumeLayout
    -0.47
    }>;
    -0.45
    staticmethod
    -0.44
    CodeAttribute
    -0.44
    /***/
    -0.43
    POSITIVE LOGITS
     vetorial
    0.66
     vettoriale
    0.65
     magnética
    0.63
    {\
    0.62
     trasparente
    0.61
     vectorielle
    0.61
    rovnik
    0.61
    giveness
    0.61
     grossesse
    0.60
     termica
    0.60
    Activations Density 1.469%

    No Known Activations