© 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. 13267
    Prev
    Next
    INDEX
    Explanations

    words related to quality, intention, and emotional states

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

    ending in "ly", "ably", "ately", "ously", or "ally"

    np_acts-logits-general · gemini-2.0-flash

    adverb formation

    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
    atalos
    -0.55
     대한
    -0.52
    soort
    -0.49
    sterious
    -0.48
    StreetMap
    -0.48
    kmäler
    -0.47
    colhead
    -0.47
    visející
    -0.46
    jší
    -0.46
    ageo
    -0.45
    POSITIVE LOGITS
    ally
    1.74
    ingly
    1.53
    ly
    1.51
    ALLY
    1.50
    ably
    1.49
    matically
    1.43
    antly
    1.42
    ically
    1.41
    ually
    1.41
    ously
    1.40
    Activations Density 0.484%

    No Known Activations