© 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. 3605
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to legal proceedings or claims

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

    following verbs indicating potential issues/actions

    np_acts-logits-general · gemini-2.0-flash

    unlawful, trumped-up, preposterous actions

    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
    ьаж
    -0.80
    Datuak
    -0.74
    oa̍t
    -0.73
    parsedMessage
    -0.71
    hyrchwyd
    -0.70
    MLLoader
    -0.69
     ExecuteAsync
    -0.68
    ंदीखरीदारी
    -0.68
    Попис
    -0.63
    tagHelperRunner
    -0.59
    POSITIVE LOGITS
     inappropriate
    1.57
     unnecessary
    1.54
     unrealistic
    1.50
     incorrect
    1.47
     unnecessarily
    1.42
     useless
    1.41
     unreasonable
    1.40
     spurious
    1.38
     ridiculous
    1.37
     improper
    1.35
    Activations Density 1.241%

    No Known Activations