© 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. 5946
    Prev
    Next
    INDEX
    Explanations

    phrases related to "one way" or directional movement

    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
    mybatisplus
    -0.99
    DockStyle
    -0.93
    :✨
    -0.85
    SourceChecksum
    -0.82
     otomatig
    -0.80
    modelBuilder
    -0.78
    bootstrapcdn
    -0.77
    featureID
    -0.75
    rungsseite
    -0.74
    GraphicsUnit
    -0.73
    POSITIVE LOGITS
     biệt
    0.56
     disposable
    0.56
     isolated
    0.53
    malige
    0.52
    logous
    0.51
    hoc
    0.51
    ServiceClient
    0.51
     pied
    0.51
     exclusive
    0.48
    Exp
    0.46
    Activations Density 0.351%

    No Known Activations