© 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. 23-GEMMASCOPE-RES-16K
    11. 2345
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    IBarButtonItem
    -0.44
    <bos>
    -0.43
     surround
    -0.38
     nawr
    -0.37
     nahilalakip
    -0.35
    WriteLiteral
    -0.35
    KURZBESCHREIBUNG
    -0.34
    penup
    -0.33
     flèche
    -0.33
    RTHOOK
    -0.32
    POSITIVE LOGITS
     censiti
    0.56
     bezeichneter
    0.55
    
    0.54
    special
    0.53
    XmlIgnore
    0.50
    +#+
    0.49
    季
    0.47
    MigrationBuilder
    0.47
     special
    0.47
    Special
    0.45
    Activations Density 0.234%

    No Known Activations