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. 22-GEMMASCOPE-RES-16K
    6. 6111
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to characters and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ffilmiau
    -0.53
     AspNetCore
    -0.47
    بالإنجليزية
    -0.46
    SharedCtor
    -0.44
     pinulongan
    -0.43
     actionMode
    -0.42
    السكان
    -0.41
    tanleria
    -0.41
    fastjson
    -0.41
    ValueStyle
    -0.40
    POSITIVE LOGITS
    ſt
    0.35
    sbericht
    0.35
     ryzen
    0.34
     Correia
    0.34
    힣
    0.34
    WP
    0.34
     révé
    0.33
    gesehen
    0.33
     whor
    0.33
     microp
    0.33
    Activations Density 0.029%

    No Known Activations