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. 4-GEMMASCOPE-RES-16K
    6. 10987
    Prev
    Next
    INDEX
    Explanations

    the concept of exclusivity 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
    MigrationBuilder
    -0.77
    InSection
    -0.71
    SBATCH
    -0.69
    DllImport
    -0.68
     дописавши
    -0.68
    Stry
    -0.67
     tartalomajánló
    -0.67
    pushFollow
    -0.67
    Personensuche
    -0.67
    TaskId
    -0.67
    POSITIVE LOGITS
     exclusive
    2.81
     Exclusive
    2.65
    Exclusive
    2.62
    exclusive
    2.53
     EXCLUSIVE
    2.34
     Exclu
    2.23
     exclusives
    2.13
    Exclu
    2.13
    EXCLUSIVE
    2.12
     exclusivity
    2.06
    Activations Density 0.080%

    No Known Activations