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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3546
    Prev
    Next
    INDEX
    Explanations

    grammatical structures and phrases related to nouns and their usage

    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
     Bowers
    -0.70
     Lewis
    -0.70
     Bernal
    -0.68
     POM
    -0.67
     Karn
    -0.66
     Dodson
    -0.66
     Hawthorne
    -0.66
     Leviathan
    -0.66
     Ved
    -0.64
    Lewis
    -0.63
    POSITIVE LOGITS
     Justin
    0.93
    Justin
    0.86
     justin
    0.85
     Bree
    0.84
    Bree
    0.81
     Pai
    0.76
    justin
    0.71
     Mandy
    0.71
     Talla
    0.70
     Kele
    0.69
    Activations Density 1.402%

    No Known Activations