© 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. 15352
    Prev
    Next
    INDEX
    Explanations

    references to quantifiable factors and metrics

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

    Follows adjectives describing positive experiences

    np_acts-logits-general · gemini-2.0-flash

    developed characters

    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
     hereinafter
    -0.64
     "<?
    -0.60
    hereinafter
    -0.59
    ');?>
    -0.57
    Rcpp
    -0.57
     című
    -0.56
    Zdra
    -0.56
     şimdi
    -0.55
    通販
    -0.55
    ścić
    -0.54
    POSITIVE LOGITS
     excellent
    0.66
    Loved
    0.66
     seemed
    0.66
     Loved
    0.65
     👍
    0.64
     snd
    0.64
     very
    0.64
    Very
    0.62
     Very
    0.62
    seemed
    0.61
    Activations Density 0.125%

    No Known Activations