© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24551
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to justifications or rationalizations

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

    excuse and excuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <em>
    -0.37
    <i>
    -0.34
     Heisenberg
    -0.33
     Most
    -0.33
    nya
    -0.32
    -0.30
    はじめに
    -0.30
    onAttach
    -0.30
    érables
    -0.29
    <strong>
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.75
     disambiguazione
    0.75
    excuse
    0.66
    Excuse
    0.66
    AndEndTag
    0.66
     Excuse
    0.65
     محفوظة
    0.63
     Wikiseite
    0.60
    InjectMocks
    0.60
    点此举报
    0.59
    Activations Density 0.004%

    No Known Activations