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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12110
    Prev
    Next
    INDEX
    Explanations

    complex discussions about choice and belief systems

    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
    oneofs
    -0.48
     Precis
    -0.35
     Def
    -0.33
    toggler
    -0.32
    kel
    -0.32
     msglen
    -0.32
     tramp
    -0.32
     Raim
    -0.31
     def
    -0.31
    setVerticalGroup
    -0.31
    POSITIVE LOGITS
     pouvoit
    0.70
     disambiguazione
    0.60
     feroit
    0.59
     auroit
    0.58
    Билгалдахарш
    0.55
     étoit
    0.55
    queryInterface
    0.55
    StoryboardSegue
    0.55
     nakalista
    0.54
    things
    0.53
    Activations Density 0.764%

    No Known Activations