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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15001
    Prev
    Next
    INDEX
    Explanations

    markup or formatting tags in text

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

    Mathematical theorems or assumptions

    np_acts-logits-general · gemini-2.0-flash

    LaTeX and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.72
    twimg
    -0.58
    +#+
    -0.56
     autorytatywna
    -0.56
    ogueira
    -0.55
     Portail
    -0.52
    zzleHttp
    -0.52
    kuuta
    -0.51
     متحده
    -0.50
    SharedDtor
    -0.50
    POSITIVE LOGITS
    </blockquote>
    0.45
    endphp
    0.41
    endpush
    0.40
     nôtre
    0.39
    FTFY
    0.36
    !
    0.35
    WriteTagHelper
    0.35
    enderror
    0.35
    endif
    0.34
    ↵↵
    0.33
    Activations Density 0.258%

    No Known Activations