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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30743
    Prev
    Next
    INDEX
    Explanations

    terms related to strategic planning and partnerships

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

    strategic + planning/action terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FormsModule
    -0.52
     mijne
    -0.50
     badkamer
    -0.48
     kantoor
    -0.47
     Fee
    -0.47
     internetu
    -0.47
     Inscrivez
    -0.47
     daarvan
    -0.46
    thenReturn
    -0.46
     aquilo
    -0.45
    POSITIVE LOGITS
    Strategic
    1.09
     Strategic
    1.06
     strategic
    1.04
    strategic
    1.03
     strateg
    0.83
     STRATEG
    0.81
     Strateg
    0.76
     estratégico
    0.75
     strategically
    0.75
    strateg
    0.75
    Activations Density 0.003%

    No Known Activations