© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8717
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "out" in a technical context, particularly within code or programming discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chyma
    -0.63
    fjspx
    -0.60
    __(/*!
    -0.60
    RenderAtEndOf
    -0.58
     AssemblyCulture
    -0.53
    yntaxException
    -0.53
     الحره
    -0.50
    pecto
    -0.49
    ❋
    -0.48
    UrlResolution
    -0.48
    POSITIVE LOGITS
     out
    0.81
     Out
    0.65
    Out
    0.65
    getOut
    0.61
    principalTable
    0.52
     OUT
    0.50
     output
    0.47
    migrationBuilder
    0.45
     input
    0.42
     оригіналу
    0.42
    Activations Density 0.311%

    No Known Activations