© 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. 39634
    Prev
    Next
    INDEX
    Explanations

    terms related to cleaning and maintenance

    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
     StringTokenizer
    -0.72
     estekak
    -0.69
    StoryboardSegue
    -0.68
     ExecuteAsync
    -0.67
     Efq
    -0.67
     caufe
    -0.66
    protoimpl
    -0.66
     nakalista
    -0.65
     cauſe
    -0.65
    RegistryLite
    -0.65
    POSITIVE LOGITS
     easy
    0.52
     mudah
    0.48
    easy
    0.48
    Novel
    0.48
     ew
    0.48
    SPATH
    0.46
     washable
    0.45
    iesa
    0.45
     Easy
    0.44
     facile
    0.44
    Activations Density 0.010%

    No Known Activations