© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5901
    Prev
    Next
    INDEX
    Explanations

    references to academic qualifications and professional positions

    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
    Билгалдахарш
    -0.82
    +#+#
    -0.80
     <<<<<<<<<<<<<<
    -0.75
    astify
    -0.74
     resourceCulture
    -0.74
    igneurs
    -0.70
    aarrggbb
    -0.69
    CppMethod
    -0.69
    Спољашње
    -0.68
     Geſch
    -0.66
    POSITIVE LOGITS
    <eos>
    0.32
     
    0.30
    .@
    0.29
     é
    0.28
    PDATE
    0.28
    serialization
    0.27
     completed
    0.25
     ا
    0.25
     cùng
    0.24
     and
    0.24
    Activations Density 0.128%

    No Known Activations