© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 5534
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting commands and syntax used in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruptedException
    -0.70
    LEGGI
    -0.62
     féd
    -0.61
     kategor
    -0.58
     delegation
    -0.57
    phazard
    -0.56
     mengen
    -0.53
    UnknownFields
    -0.53
     Volu
    -0.53
    athione
    -0.53
    POSITIVE LOGITS
     fain
    0.61
    
    0.60
    ⓘ
    0.59
    MessageOf
    0.57
     VizieR
    0.56
    crites
    0.55
    SizeF
    0.55
    Eksteraj
    0.55
    ViewChild
    0.53
    INLINE
    0.53
    Activations Density 1.546%

    No Known Activations