© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 480
    Prev
    Next
    INDEX
    Explanations

    logical indicators, specifically concerning conditions of truth and falsehood within a structured context

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

    mathematical or logical operations, especially comparisons and boolean logic statements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     autorytatywna
    -0.77
    ftagPool
    -0.73
     kasarigan
    -0.73
    OGND
    -0.72
    verifyException
    -0.66
    ロウィン
    -0.61
    principalTable
    -0.61
    __(/*!
    -0.61
    下载附件
    -0.59
    CppMethod
    -0.58
    POSITIVE LOGITS
     also
    0.56
     außerdem
    0.45
     others
    0.39
     likewise
    0.39
     another
    0.39
     ayrıca
    0.38
     furthermore
    0.38
     additionally
    0.38
     Bo
    0.37
     then
    0.37
    Activations Density 0.666%

    No Known Activations