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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 2458
    Prev
    Next
    INDEX
    Explanations

    segments of code related to data processing and manipulation

    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
    Mer
    -0.38
    INF
    -0.37
     juge
    -0.36
    vidia
    -0.36
     sáb
    -0.36
     наре
    -0.35
     eten
    -0.35
     Mer
    -0.35
    引っ
    -0.35
     Liberal
    -0.35
    POSITIVE LOGITS
     InputDecoration
    0.75
    ReusableCell
    0.64
    InSection
    0.53
     MainAxisSize
    0.52
    mybatisplus
    0.52
    ConstraintMaker
    0.51
     Chwiliwch
    0.50
     resourceCulture
    0.50
     oprot
    0.49
     pinulongan
    0.47
    Activations Density 0.450%

    No Known Activations