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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16141
    Prev
    Next
    INDEX
    Explanations

    references to practical applications and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iStock
    -0.53
    row
    -0.51
    iség
    -0.51
    sproz
    -0.50
     autores
    -0.45
    oneofs
    -0.44
     společnost
    -0.44
    fatta
    -0.43
    ing
    -0.43
     kre
    -0.43
    POSITIVE LOGITS
    practical
    0.98
     practical
    0.98
     Practical
    0.92
    Practical
    0.91
     realities
    0.90
     práctico
    0.89
     practicality
    0.89
     prag
    0.86
     PRACTICAL
    0.86
    ctical
    0.82
    Activations Density 0.265%

    No Known Activations