© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14654
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and experimental methodologies

    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
     BIBSYS
    -0.45
    staticmethod
    -0.43
     incompati
    -0.42
     androidx
    -0.42
    ństw
    -0.41
     meinte
    -0.40
     CURIAM
    -0.40
    RTEX
    -0.40
    spě
    -0.40
     vs
    -0.40
    POSITIVE LOGITS
    EndInit
    0.82
    InjectAttribute
    0.75
    principalColumn
    0.67
    PerformLayout
    0.64
    GroupLayout
    0.64
    abestanden
    0.63
    CodeAttribute
    0.63
    ыгана
    0.63
     stages
    0.60
     Roskov
    0.60
    Activations Density 0.314%

    No Known Activations