Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15609
    Prev
    Next
    INDEX
    Explanations

    specific syntax and structure in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.61
     برانيه
    -0.60
     houſe
    -0.54
    withIdentifier
    -0.51
    󠁢
    -0.50
     ſch
    -0.50
     Reſ
    -0.49
     greateſt
    -0.49
     Perſ
    -0.48
     Majefty
    -0.48
    POSITIVE LOGITS
    Filmografie
    0.47
    ungsver
    0.44
     defaultstate
    0.41
    WriteTagHelper
    0.41
    olverine
    0.40
     modalités
    0.37
    iocene
    0.36
     Veranstaltung
    0.36
     siyang
    0.36
    haikusbot
    0.36
    Activations Density 1.526%

    No Known Activations