© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    syntactic structures or patterns, particularly involving references or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     — 
    -0.45
     αντι
    -0.45
    انگلیسی
    -0.44
     “
    -0.42
     jembatan
    -0.41
     içeris
    -0.40
     threat
    -0.40
     lucru
    -0.39
     Newtonsoft
    -0.39
    iredo
    -0.37
    POSITIVE LOGITS
    ########.
    0.89
    AndEndTag
    0.76
     Daß
    0.74
    GTCX
    0.71
    oredCriteria
    0.70
    smithy
    0.69
    SizeF
    0.68
     InputDecoration
    0.67
     iNdEx
    0.66
    ynie
    0.66
    Activations Density 0.924%

    No Known Activations