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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5928
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to information and data processing

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

    Prefixes: dif-, com-, pro-, ac-, sig-, permis-

    np_acts-logits-general · gemini-2.0-flash

    prefix patterns like dif- com- pro- hun- ac- permis- signifi-

    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
    ſelf
    -1.07
    wiſe
    -1.00
    neſs
    -0.99
     Majefty
    -0.97
    NUMX
    -0.97
     itſelf
    -0.94
     myſelf
    -0.94
    ſelves
    -0.91
    enumii
    -0.90
    eſt
    -0.90
    POSITIVE LOGITS
    -
    0.75
    ∣
    0.64
    ↵
    0.62
    -,
    0.61
    ↵↵
    0.58
    -.
    0.57
    <eos>
    0.54
    "
    0.53
     independencia
    0.53
    ¬
    0.51
    Activations Density 0.248%

    No Known Activations