© 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. 23-GEMMASCOPE-RES-16K
    6. 4351
    Prev
    Next
    INDEX
    Explanations

    references to layered structures or techniques in visual art and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.68
     htons
    -0.66
    DataAnnotations
    -0.63
     CreateTagHelper
    -0.61
    tagHelperRunner
    -0.60
    WriteAttribute
    -0.60
    MigrationBuilder
    -0.59
     springfox
    -0.59
     Schrauben
    -0.57
    tamol
    -0.57
    POSITIVE LOGITS
     sheet
    1.42
     sheets
    1.35
    sheet
    1.22
     Sheet
    1.13
     SHEET
    1.07
    sheets
    1.06
     Sheets
    1.05
     panel
    1.03
    Sheet
    1.02
    heet
    1.02
    Activations Density 0.585%

    No Known Activations