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. 24-GEMMASCOPE-RES-16K
    6. 12638
    Prev
    Next
    INDEX
    Explanations

    URLs and references related to GitHub, coding, or technical content

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

    Code, URLs, and file paths

    np_acts-logits-general · gemini-2.0-flash

    GitHub issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IN
    -1.55
    in
    -1.33
    In
    -1.30
     In
    -1.27
     IN
    -1.23
    イン
    -1.14
    getIn
    -1.13
    İN
    -1.02
     inlay
    -0.96
    ÍN
    -0.94
    POSITIVE LOGITS
     nella
    0.45
    abbé
    0.41
    المناصب
    0.39
    ису
    0.39
     dans
    0.39
    mtable
    0.38
     gants
    0.38
     '''
    0.37
    puta
    0.37
    pyx
    0.36
    Activations Density 0.885%

    No Known Activations