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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10060
    Prev
    Next
    INDEX
    Explanations

    exclamatory punctuation and expressions of surprise or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ede
    -0.72
     Rump
    -0.66
    ation
    -0.64
    böz
    -0.64
     Sund
    -0.64
    "):
    
    -0.63
    SHADOW
    -0.63
    ings
    -0.63
    aure
    -0.62
     FontWeight
    -0.61
    POSITIVE LOGITS
    %!
    2.05
    !
    1.92
    ?!?
    1.87
     !
    1.79
    !”
    1.74
    !"
    1.74
    !!!!!!
    1.73
    !!!!!!!
    1.72
    !
    1.71
    ”!
    1.69
    Activations Density 0.082%

    No Known Activations