© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38625
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and names

    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
    AndEndTag
    -0.58
     megjelen
    -0.54
    bruch
    -0.54
     œil
    -0.53
    atero
    -0.52
    bahasa
    -0.52
    perties
    -0.51
     вс
    -0.50
    enumii
    -0.49
    graaf
    -0.49
    POSITIVE LOGITS
    олові
    0.60
     predeceased
    0.57
    ClientSize
    0.55
     onAnimation
    0.53
    LoggerFactory
    0.51
     ElementRef
    0.51
    ToAction
    0.50
    rungsseite
    0.49
    */].
    0.48
    RefNanny
    0.48
    Activations Density 0.002%

    No Known Activations