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. 15-GEMMASCOPE-RES-16K
    6. 1522
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with education or administrative positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.70
     BoxDecoration
    -0.69
    ագրություններ
    -0.62
    awtextra
    -0.61
    AxisAlignment
    -0.61
     Calor
    -0.59
     CURLOPT
    -0.57
    Pall
    -0.57
    RenderAtEndOf
    -0.57
    LookAnd
    -0.55
    POSITIVE LOGITS
    ContentAlignment
    0.53
    chdir
    0.49
     K
    0.49
    ネマ
    0.47
    Искәрмәләр
    0.47
     M
    0.46
     astore
    0.45
    Tento
    0.45
     Mar
    0.44
     R
    0.43
    Activations Density 0.267%

    No Known Activations