© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8941
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in data

    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
     juſ
    -0.42
     reaſon
    -0.41
     houſe
    -0.40
     pleaſure
    -0.40
     raiſ
    -0.40
    #
    -0.39
     razon
    -0.36
     barb
    -0.35
     Benutz
    -0.35
    naments
    -0.35
    POSITIVE LOGITS
     виправивши
    0.59
    tagHelperRunner
    0.59
    istoitu
    0.55
    Билгалдахарш
    0.54
     незавершена
    0.54
     HasFactory
    0.54
     ffilmiau
    0.54
     שוליים
    0.53
     ostavi
    0.52
     محفوظة
    0.50
    Activations Density 0.251%

    No Known Activations