© 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. 8261
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences regarding treatment and recovery from substance use or addiction

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

    after auxiliary verbs/contractions

    np_acts-logits-general · gemini-2.0-flash

    profanity and negative sentiment

    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
     quelquefois
    -0.82
     quæ
    -0.71
     Moslem
    -0.69
    ﹗
    -0.68
     occorre
    -0.65
     Usted
    -0.64
     vícti
    -0.63
     extraordinario
    -0.62
     auffi
    -0.61
     soltanto
    -0.61
    POSITIVE LOGITS
     shitty
    1.35
     idk
    1.30
     fucking
    1.24
     fucked
    1.22
     Idk
    1.20
     tbh
    1.18
    idk
    1.15
     FUCKING
    1.15
     shit
    1.11
     fuck
    1.11
    Activations Density 1.312%

    No Known Activations