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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85617
    Prev
    Next
    INDEX
    Explanations

    numerical data and results

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

    sentence terminators

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     transfieras
    -0.89
     насељу
    -0.74
    AndEndTag
    -0.69
     ſta
    -0.66
    يكب
    -0.66
    NameInMap
    -0.62
    RenderAtEndOf
    -0.61
    webElementXpaths
    -0.61
     desmotivaciones
    -0.59
     '\\;'
    -0.59
    POSITIVE LOGITS
    lash
    0.38
     refroidissement
    0.36
    стру
    0.35
     ARISING
    0.34
    もしろ
    0.34
     whil
    0.32
     COOL
    0.32
    pass
    0.32
     Boc
    0.32
    pec
    0.31
    Activations Density 0.240%

    No Known Activations