Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 45820
    Prev
    Next
    INDEX
    Explanations

    references to "regard" or related discussions about perspectives and considerations

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

    introduces a specific context

    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
    styleType
    -0.49
    ecos
    -0.48
    chito
    -0.47
    ssi
    -0.46
    sme
    -0.46
    rostis
    -0.46
    vic
    -0.45
    bens
    -0.45
    UserScript
    -0.45
    nically
    -0.44
    POSITIVE LOGITS
     regard
    1.84
     Regard
    1.49
    regard
    1.48
     REGARD
    1.11
     regards
    0.93
     riguardo
    0.85
    regards
    0.82
     Hinsicht
    0.81
     égard
    0.77
     Hinblick
    0.71
    Activations Density 0.004%

    No Known Activations