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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6569
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to medical and physiological effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     physical
    -0.47
     spatial
    -0.45
    physical
    -0.45
    Physical
    -0.43
     physically
    -0.43
     Physical
    -0.42
     físicos
    -0.42
     Physically
    -0.41
     geographic
    -0.41
    PHYSICAL
    -0.41
    POSITIVE LOGITS
    ArrowToggle
    0.71
    ftagPool
    0.60
     ExecuteAsync
    0.59
     HttpNotFound
    0.57
     فريبيس
    0.56
    fjspx
    0.53
    MemoryWarning
    0.52
     duele
    0.49
     gynhyrchwyd
    0.48
    AddTagHelper
    0.48
    Activations Density 3.500%

    No Known Activations