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. 6017
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation and symbols

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

    LaTeX or code within text

    np_acts-logits-general · gemini-2.0-flash

    special characters, math, code

    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
     étend
    -0.68
    </i>
    -0.63
    </b>
    -0.62
     NgModule
    -0.61
     ?
    -0.57
     GBIF
    -0.55
    ?</
    -0.55
    ]</
    -0.55
     prezzi
    -0.54
     незавершена
    -0.54
    POSITIVE LOGITS
    <em>
    0.92
    DoubleQuotes
    0.63
    +#+
    0.54
    /*
    0.52
     Issus
    0.51
    withOpacity
    0.51
    astéro
    0.51
     متعلقه
    0.49
     <<<<<<<<<<<<<<
    0.49
     estekak
    0.47
    Activations Density 0.024%

    No Known Activations