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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5805
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress tracking and indicators

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

    progress and advancement

    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
    <bos>
    -0.72
    1
    -0.41
    She
    -0.37
     whome
    -0.35
    He
    -0.34
     whom
    -0.34
     mesin
    -0.32
     marrying
    -0.31
    To
    -0.31
    2
    -0.30
    POSITIVE LOGITS
     Progress
    2.41
    Progress
    2.30
     progress
    2.27
    progress
    2.23
     PROGRESS
    2.06
    PROGRESS
    1.85
     progreso
    1.66
    setProgress
    1.61
     progresso
    1.59
    进度
    1.50
    Activations Density 0.010%

    No Known Activations