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. 23-GEMMASCOPE-RES-16K
    6. 4953
    Prev
    Next
    INDEX
    Explanations

    details related to contact information and service descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighborhood
    -0.92
    Neighbors
    -0.82
    Rumors
    -0.79
    neighborhood
    -0.77
     colors
    -0.76
     Rumors
    -0.74
     neighborhood
    -0.73
     color
    -0.72
     behavior
    -0.72
     rumor
    -0.72
    POSITIVE LOGITS
     £
    1.31
     Whilst
    1.18
    Whilst
    1.17
    £
    1.11
     enquiries
    1.10
    initialise
    1.03
     (£
    0.96
    -£
    0.95
     Enquiries
    0.95
     bespoke
    0.92
    Activations Density 0.132%

    No Known Activations