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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7901
    Prev
    Next
    INDEX
    Explanations

    specific gene symbols and their related annotations in biological texts

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

    Taxonomic abbreviation

    np_acts-logits-general · gemini-2.0-flash

    organismal species names

    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
     purpoſe
    -1.77
     houſe
    -1.70
     pleaſure
    -1.69
     myſelf
    -1.68
     itſelf
    -1.65
     ſche
    -1.63
     ſtate
    -1.62
     raiſ
    -1.62
     ſta
    -1.61
     ſever
    -1.60
    POSITIVE LOGITS
     sp
    0.73
     ta
    0.57
     z
    0.57
     s
    0.56
     la
    0.56
     b
    0.55
     vi
    0.55
     m
    0.54
     x
    0.54
     p
    0.54
    Activations Density 0.264%

    No Known Activations