© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5662
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and proper nouns

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

    Followed by "ider", "rough", "olu", "izi", or "inawa"

    np_acts-logits-general · gemini-2.0-flash

    place 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
    ,
    -0.59
     
    -0.58
     (
    -0.53
     the
    -0.51
     ,
    -0.51
     next
    -0.50
    :].
    -0.50
     for
    -0.50
     with
    -0.49
    <eos>
    -0.49
    POSITIVE LOGITS
     Majefty
    0.91
     Efq
    0.85
     مرئيه
    0.76
     doubtnut
    0.76
    OGND
    0.76
     TextAppearance
    0.75
     purpoſe
    0.74
     Partagez
    0.72
    τογραφ
    0.70
    ſelves
    0.70
    Activations Density 0.283%

    No Known Activations