© 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. 4-GEMMASCOPE-RES-16K
    11. 3298
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unique" in various contexts

    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
     censura
    -0.70
     toros
    -0.64
    FieldDescriptor
    -0.61
    </em>
    -0.60
    <em>
    -0.59
     fós
    -0.57
    usser
    -0.57
    oughed
    -0.56
    shi
    -0.56
     Shepard
    -0.55
    POSITIVE LOGITS
     unique
    2.11
    unique
    2.07
     Unique
    2.02
     UNIQUE
    2.02
    Unique
    1.99
    UNIQUE
    1.86
     uniques
    1.84
     uniqueness
    1.75
     uniqu
    1.68
     uniquely
    1.63
    Activations Density 0.041%

    No Known Activations