© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8388
    Prev
    Next
    INDEX
    Explanations

    references to web browser and usage errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -0.79
     Chwiliwch
    -0.60
    ThroughAttribute
    -0.50
    .*")]
    -0.48
    })`
    -0.46
    Искәрмәләр
    -0.46
    addCriterion
    -0.46
    Referanser
    -0.45
     snippetHide
    -0.44
    msgTypes
    -0.43
    POSITIVE LOGITS
     ועל
    1.41
     وعلى
    1.13
     behalf
    1.11
     occasions
    0.91
     occasion
    0.88
     basis
    0.72
    basis
    0.62
     grounds
    0.62
     fronts
    0.61
     occas
    0.58
    Activations Density 0.658%

    No Known Activations