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. 10-GEMMASCOPE-RES-16K
    6. 15572
    Prev
    Next
    INDEX
    Explanations

    references to interests and their implications 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 @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scriptcase
    -0.80
    izop
    -0.71
    ophanes
    -0.70
     Faber
    -0.67
    DNEY
    -0.67
     Dumas
    -0.66
     Maw
    -0.64
     Vaticano
    -0.63
    Madeleine
    -0.63
    dhury
    -0.63
    POSITIVE LOGITS
     Interest
    1.98
     interest
    1.97
     interests
    1.92
    Interest
    1.88
     INTEREST
    1.83
     Interests
    1.81
    interest
    1.78
    INTEREST
    1.68
    Interests
    1.60
    interests
    1.51
    Activations Density 0.068%

    No Known Activations