© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10802
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional cases in programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibouti
    -0.70
    }]
    -0.65
    abestanden
    -0.59
    openSession
    -0.58
    ()}>
    -0.58
    picuous
    -0.57
    ']?>
    -0.57
     Snape
    -0.55
    adaptiveStyles
    -0.54
    )()
    -0.54
    POSITIVE LOGITS
    case
    2.87
    Case
    1.95
     case
    1.94
     Case
    1.91
    CASE
    1.89
     CASE
    1.73
    cases
    1.65
     Cases
    1.47
    Cases
    1.41
     cases
    1.40
    Activations Density 0.038%

    No Known Activations