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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6497
    Prev
    Next
    INDEX
    Explanations

    terms related to the Hashishin or assassins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.63
     eens
    -0.62
    醐
    -0.62
    IBinder
    -0.61
     Solitude
    -0.61
    ENTRE
    -0.60
    Ска
    -0.59
    出版年
    -0.59
    etern
    -0.58
    bootstrapcdn
    -0.58
    POSITIVE LOGITS
    ash
    0.69
    ASH
    0.66
     Tash
    0.63
    ingly
    0.59
     ASH
    0.58
    kesan
    0.58
     DASH
    0.56
     Bash
    0.56
    Ash
    0.54
     Osh
    0.53
    Activations Density 0.102%

    No Known Activations