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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 69158
    Prev
    Next
    INDEX
    Explanations

    code snippets that include return statements

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

    code snippets and technical jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IActionResult
    -0.48
    iſen
    -0.48
     pleaſure
    -0.47
    :✨
    -0.47
    paraíso
    -0.46
     harbour
    -0.45
    KindOfClass
    -0.45
     contextLoads
    -0.45
    蚪
    -0.44
     indígen
    -0.44
    POSITIVE LOGITS
    angliski
    0.44
    PYX
    0.41
    Décès
    0.40
    MessageTagHelper
    0.39
    Just
    0.39
     pylint
    0.39
     Just
    0.38
    DispatchToProps
    0.37
     autorytatywna
    0.36
     Lain
    0.36
    Activations Density 0.003%

    No Known Activations