Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15678
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unique" and its variations, suggesting a focus on originality and distinctiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    -0.62
     Mors
    -0.62
    стма
    -0.59
    <code>
    -0.57
    Để
    -0.57
    BlockPos
    -0.56
    FieldDescriptor
    -0.56
    shi
    -0.55
     fós
    -0.55
    ber
    -0.55
    POSITIVE LOGITS
     UNIQUE
    1.23
    UNIQUE
    1.18
     uniqu
    1.17
     uniques
    1.15
    UniqueId
    1.13
     Unique
    1.11
     unique
    1.10
    unique
    1.10
     uniqueness
    1.08
    Unique
    1.04
    Activations Density 0.056%

    No Known Activations