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. 22-GEMMASCOPE-RES-16K
    6. 12788
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and experimental setups involving mice and other biological elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Al" or "AL"

    np_acts-logits-general · gemini-2.0-flash

    ali, al, allotment, acreage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reaper
    -0.61
     Cypri
    -0.54
     pö
    -0.54
     reaper
    -0.53
     diode
    -0.53
     obsidian
    -0.52
     MediatR
    -0.52
     Gött
    -0.52
    Reaper
    -0.52
     Hek
    -0.51
    POSITIVE LOGITS
     AL
    2.04
     Al
    1.82
    Al
    1.66
     Ali
    1.50
    AL
    1.50
     al
    1.48
     Ал
    1.48
     Alb
    1.44
     Allie
    1.42
    Ali
    1.41
    Activations Density 0.360%

    No Known Activations