© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9452
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in code snippets or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.84
    detectChanges
    -0.65
     ब्रेकडाउन
    -0.63
     gynhyrchwyd
    -0.63
    MessageTagHelper
    -0.63
    RegistryLite
    -0.60
     ProtoMessage
    -0.60
     betweenstory
    -0.59
    Obrázky
    -0.58
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
    },[])
    0.53
    antaranya
    0.53
     senare
    0.53
    himovic
    0.52
    anyeol
    0.50
     tuer
    0.48
    mantec
    0.47
    гән
    0.47
    =").
    0.47
    енча
    0.46
    Activations Density 0.290%

    No Known Activations