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. 5-GEMMASCOPE-RES-16K
    6. 2547
    Prev
    Next
    INDEX
    Explanations

    phrases that describe roles and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))$.
    -0.74
     ardından
    -0.71
     avenida
    -0.69
    $
    
    -0.68
    ()]);
    -0.67
    $")
    -0.66
    APTER
    -0.66
     estadounidenses
    -0.65
     Petrus
    -0.65
     $:$
    -0.65
    POSITIVE LOGITS
     role
    2.56
     roles
    2.34
     Role
    2.31
     ROLE
    2.31
    Role
    2.19
     Roles
    2.19
    role
    2.08
    ROLE
    1.99
     getRole
    1.92
    Roles
    1.86
    Activations Density 0.050%

    No Known Activations