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. 20-GEMMASCOPE-RES-16K
    6. 9543
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]:
    
    -0.55
     also
    -0.48
     nakalista
    -0.48
     others
    -0.48
     folgender
    -0.47
     finally
    -0.46
     was
    -0.46
     another
    -0.45
     outra
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    POSITIVE LOGITS
    FunctionFlags
    0.73
     GenerationType
    0.71
    isms
    0.69
     թվական
    0.66
    IndentedString
    0.65
    nosaurus
    0.64
    kuuta
    0.64
    crollView
    0.63
    SaveChangesAsync
    0.62
    HttpPut
    0.62
    Activations Density 0.826%

    No Known Activations