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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10230
    Prev
    Next
    INDEX
    Explanations

    elements that are identifiers or tags in a code or data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal identifiers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal identifiers and strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    enumi
    -0.71
     resourceCulture
    -0.71
    flage
    -0.61
    eer
    -0.59
     يتيمه
    -0.58
     BorderSide
    -0.56
    glBindTexture
    -0.52
    İstinadlar
    -0.52
    Rè
    -0.52
    اریخ
    -0.51
    POSITIVE LOGITS
    __":
    0.57
    ef
    0.54
    Bif
    0.54
     desaf
    0.53
    __':
    
    0.53
     desafi
    0.53
     Tuff
    0.53
     chré
    0.52
    ed
    0.51
     Bif
    0.51
    Activations Density 0.410%

    No Known Activations