© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1955
    Prev
    Next
    INDEX
    Explanations

    phrases expressing success or achievement in managing tasks or goals

    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
    achal
    -0.65
    setVerticalGroup
    -0.64
     CURIAM
    -0.61
    AccessorTable
    -0.61
    Geri
    -0.60
    endpush
    -0.60
     opcion
    -0.58
    Pró
    -0.58
    WebVitals
    -0.57
    DebuggerNonUser
    -0.56
    POSITIVE LOGITS
     consegui
    0.82
     conseguiu
    0.73
     consegue
    0.72
     lograron
    0.70
     Somehow
    0.66
     logrado
    0.63
     somehow
    0.63
     удалось
    0.62
    Somehow
    0.61
     berhasil
    0.61
    Activations Density 0.217%

    No Known Activations