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. 9131
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive sentiments

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

    Code, lists, and non-English characters

    np_acts-logits-general · gemini-2.0-flash

    CMakeLists.txt or programming file names

    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
    帖最后由
    -0.39
    rawdę
    -0.38
    новништво
    -0.38
     miniaturka
    -0.38
    aarrggbb
    -0.37
    AsUp
    -0.37
     CanadaChoose
    -0.37
    ByVersion
    -0.35
     onOptions
    -0.35
    WithIOException
    -0.35
    POSITIVE LOGITS
     الحره
    0.58
     AssemblyCompany
    0.57
     متعلقه
    0.55
    \{\\
    0.53
    istoitu
    0.50
    FormTagHelper
    0.47
    Hozzáférés
    0.47
     nakalista
    0.46
    ).$
    0.45
    ')));
    0.44
    Activations Density 0.656%

    No Known Activations