© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3960
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and structure definitions

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

    Closing parenthesis characters

    np_acts-logits-general · gemini-2.0-flash

    code syntax endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused60>
    -0.54
    ();*/
    -0.53
    <unused61>
    -0.53
    </s>
    -0.52
     [...]
    -0.51
    <unused63>
    -0.50
    </blockquote>
    -0.48
    </em>
    -0.47
    :...
    -0.46
    ÁF
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.87
     unknownFields
    0.86
     resourceCulture
    0.84
    awtextra
    0.84
    JNIEnv
    0.82
    ConstraintMaker
    0.81
     ModelExpression
    0.79
     NgModule
    0.78
     BoxDecoration
    0.75
     propOrder
    0.74
    Activations Density 1.319%

    No Known Activations