© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10609
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical results in a scientific context

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

    Fractions

    np_acts-logits-general · gemini-2.0-flash

    out of / fractions

    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
    expandindo
    -0.82
     Biôgrafia
    -0.69
     utafitiHapana
    -0.68
    UserScript
    -0.68
    StoryboardSegue
    -0.67
    évaluateur
    -0.65
     eventdata
    -0.63
    دانشنامهٔ
    -0.63
    ">:
    -0.61
    Personensuche
    -0.60
    POSITIVE LOGITS
     out
    1.89
    out
    1.29
     outta
    1.10
     Out
    1.05
     из
    1.05
     OUT
    1.00
    Out
    0.99
     מתוך
    0.94
     among
    0.94
     parmi
    0.84
    Activations Density 0.383%

    No Known Activations