© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3486
    Prev
    Next
    INDEX
    Explanations

    terms related to project management and production oversight

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

    words and phrases related to project management, timelines, delays, and completion of work.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    pattern
    -0.38
    دانشنامهٔ
    -0.38
     patterns
    -0.36
     PATTERN
    -0.35
     Pattern
    -0.33
     leeftijd
    -0.33
     Patterns
    -0.32
     pattern
    -0.32
    HtmlAttribute
    -0.31
    anoic
    -0.30
    POSITIVE LOGITS
     deadlines
    1.23
     deadline
    1.11
     deliverables
    1.09
     timeline
    1.08
     timelines
    1.07
     delays
    0.97
     milestones
    0.94
     schedule
    0.91
     timetable
    0.90
    deadline
    0.87
    Activations Density 0.381%

    No Known Activations