© 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. 2-GEMMASCOPE-RES-16K
    11. 15260
    Prev
    Next
    INDEX
    Explanations

    expressions of uniqueness or distinctiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censura
    -0.61
     fós
    -0.58
     scold
    -0.56
    ędzy
    -0.56
     ladite
    -0.55
     inves
    -0.55
    ConstraintMaker
    -0.53
    shi
    -0.53
     devriez
    -0.53
    InlineData
    -0.53
    POSITIVE LOGITS
     unique
    3.17
    unique
    2.96
     Unique
    2.89
    Unique
    2.84
     UNIQUE
    2.75
    UNIQUE
    2.50
     uniques
    2.41
     uniqueness
    2.38
     uniquely
    2.25
     unieke
    2.20
    Activations Density 0.056%

    No Known Activations