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. 9-GEMMASCOPE-RES-16K
    6. 3259
    Prev
    Next
    INDEX
    Explanations

    instances of code structure and syntax, particularly in programming languages

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

    Code, special characters, and markup

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and symbols

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     betweenstory
    -0.62
    transQ
    -0.60
     שוליים
    -0.57
    bootstrapcdn
    -0.55
    WriteTagHelper
    -0.54
    aktery
    -0.54
    ritzau
    -0.52
     PagesJaunes
    -0.52
    OGND
    -0.52
    alakip
    -0.52
    POSITIVE LOGITS
    \{\\
    0.54
     <<<<<<<<<<<<<<
    0.50
    //
    0.47
    //
    0.44
    ///
    0.39
    [toxicity=0]
    0.39
    +":
    0.38
     Meno
    0.37
    __(/*!
    0.36
    cieli
    0.36
    Activations Density 0.206%

    No Known Activations