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. 25-GEMMASCOPE-RES-16K
    6. 5778
    Prev
    Next
    INDEX
    Explanations

    instances of the word "change" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.57
    vinger
    -0.49
     تانيه
    -0.49
    InitStruct
    -0.49
    matchCondition
    -0.46
    存于互联网档案馆
    -0.46
    RAINE
    -0.45
    bono
    -0.45
     linkovi
    -0.44
     choosing
    -0.44
    POSITIVE LOGITS
     direction
    0.80
     course
    0.78
     drastically
    0.76
    over
    0.74
     radically
    0.70
     diapers
    0.69
    แป
    0.69
     bieg
    0.68
     gears
    0.67
     directions
    0.67
    Activations Density 0.320%

    No Known Activations