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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 42907
    Prev
    Next
    INDEX
    Explanations

    terms related to supervised practices and processes, particularly in the context of visitation and release in legal or support settings

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

    supervised release and method

    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
    IndentedString
    -0.59
    EDEFAULT
    -0.57
    RegressionTest
    -0.55
    Tikang
    -0.52
     gynhyrchwyd
    -0.49
    EndGlobalSection
    -0.47
     validamos
    -0.46
     дописавши
    -0.46
     оригіналу
    -0.44
    rungsseite
    -0.44
    POSITIVE LOGITS
     supervised
    0.53
    supervised
    0.46
    Paid
    0.44
     regulated
    0.44
    Guided
    0.44
     guided
    0.43
     Guided
    0.42
     structured
    0.42
     controlled
    0.41
    weetened
    0.41
    Activations Density 0.258%

    No Known Activations