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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 56907
    Prev
    Next
    INDEX
    Explanations

    prepositions, particularly the word "of."

    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
    cookieParser
    -0.56
    isissez
    -0.51
     Pala
    -0.48
    utenant
    -0.46
    imal
    -0.46
    icorn
    -0.46
    getContent
    -0.43
     arvo
    -0.43
     hoek
    -0.43
    ואה
    -0.43
    POSITIVE LOGITS
     Roskov
    1.16
    Datuak
    0.93
    Aholisi
    0.92
    ########.
    0.90
    IUrlHelper
    0.86
     חיצוניים
    0.86
     مرئيه
    0.85
    
    0.84
    setVerticalGroup
    0.82
    MigrationBuilder
    0.80
    Activations Density 0.000%

    No Known Activations