© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4760
    Prev
    Next
    INDEX
    Explanations

    programming syntax and code structures

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

    Code snippets/endings

    np_acts-logits-general · gemini-2.0-flash

    JavaScript code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })();
    -0.36
    好吗
    -0.36
    ")]
    -0.36
     avoient
    -0.34
    ")));
    -0.33
     Pedersen
    -0.33
     khuyên
    -0.33
     fährt
    -0.32
     HomeComponent
    -0.32
    точници
    -0.32
    POSITIVE LOGITS
     nakalista
    0.83
     Exacts
    0.75
    sizeCache
    0.75
    NameInMap
    0.68
    AndEndTag
    0.68
    InputBorder
    0.64
     resourceCulture
    0.63
    yntaxException
    0.62
     kasarigan
    0.61
    HasAnnotation
    0.60
    Activations Density 0.119%

    No Known Activations