Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57269
    Prev
    Next
    INDEX
    Explanations

    the beginning of text segments

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     […]
    -0.78
     
    -0.55
    ↵↵
    -0.47
     co
    -0.47
    co
    -0.46
     C
    -0.46
     Co
    -0.44
     [...]
    -0.44
    </blockquote>
    -0.43
     A
    -0.42
    POSITIVE LOGITS
     Савезне
    1.60
    sizeCache
    1.24
     Efq
    1.19
    kloped
    1.14
    fillType
    1.12
     HasFactory
    1.10
    SequentialGroup
    1.09
     Мексичка
    1.09
     unknownFields
    1.09
     autorytatywna
    1.07
    Activations Density 0.000%

    No Known Activations