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. 14918
    Prev
    Next
    INDEX
    Explanations

    numerical references or dates

    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
    fjspx
    -0.59
     &___
    -0.59
    fastjson
    -0.54
    [];
    
    -0.53
    Diweddarwch
    -0.51
    Reprints
    -0.51
    _));
    -0.50
    macy
    -0.50
     ?',
    -0.50
     StringTokenizer
    -0.50
    POSITIVE LOGITS
    Kjelder
    0.54
     arşivlendi
    0.54
    OCCURRED
    0.47
    তথ্যসূত্র
    0.45
     peuples
    0.44
    Izvori
    0.36
     avven
    0.35
     armées
    0.35
     courir
    0.35
     réunis
    0.35
    Activations Density 0.199%

    No Known Activations