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. 1577
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating personal experience or identity

    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
    <bos>
    -0.82
     kasarigan
    -0.74
    IndentedString
    -0.67
    NameInMap
    -0.62
     noix
    -0.59
    ainville
    -0.56
     мәкал
    -0.56
    WithIOException
    -0.55
     gepubliceerd
    -0.53
     AspNetCore
    -0.52
    POSITIVE LOGITS
    Encyclopædia
    0.71
    layoutControl
    0.69
    LEncoder
    0.69
     ever
    0.68
    }\]
    0.68
    "):
    
    0.67
     TextInputType
    0.67
     المعل
    0.65
    ercises
    0.65
     they
    0.65
    Activations Density 0.378%

    No Known Activations