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

    Neuronpedia

    APICircuit 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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16082
    Prev
    Next
    INDEX
    Explanations

    terms related to forces and their interactions in physical systems

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

    "force"

    np_acts-logits-general · gemini-2.0-flash

    force, forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    MigrationBuilder
    -0.69
     betweenstory
    -0.61
     ब्रेकडाउन
    -0.56
     Infórmanos
    -0.53
    出版年
    -0.52
    ChildScrollView
    -0.52
    complexContent
    -0.52
    complexType
    -0.52
     NSCoder
    -0.52
    GEBURTSDATUM
    -0.51
    POSITIVE LOGITS
     forces
    1.38
     force
    1.33
     gravity
    1.21
     Forces
    1.17
    Forces
    1.16
    forces
    1.13
    force
    1.11
     Force
    1.10
    Force
    1.09
     FORCES
    1.06
    Activations Density 0.734%

    No Known Activations