© 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. 24-GEMMASCOPE-RES-16K
    6. 4279
    Prev
    Next
    INDEX
    Explanations

    specific version numbers and identifiers related to software and programming languages

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

    Microsoft-related Visual Studio errors or code

    np_acts-logits-general · gemini-2.0-flash

    visual studio, outlook, spss

    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
    Revenir
    -0.59
     DialogInterface
    -0.59
    مانی
    -0.57
    adhyay
    -0.55
     onPostExecute
    -0.54
    Espèce
    -0.53
    itinéraire
    -0.52
     Derecho
    -0.51
    isContained
    -0.51
    ValueStyle
    -0.51
    POSITIVE LOGITS
     trône
    0.58
    carteles
    0.55
     carottes
    0.53
     credere
    0.53
     mû
    0.52
    FieldBuilder
    0.52
     sogni
    0.50
    المناصب
    0.49
     automatiquement
    0.49
     pegatina
    0.47
    Activations Density 1.165%

    No Known Activations