© 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. 7669
    Prev
    Next
    INDEX
    Explanations

    sections containing technical or diagnostic terms related to medical concepts

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

    "types", "advantages", or "characteristics"

    np_acts-logits-general · gemini-2.0-flash

    explaining characteristics, types, and reasons

    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
     decidedly
    -0.52
     borealis
    -0.51
     NSCoder
    -0.46
     sauvage
    -0.45
     sentirse
    -0.44
     elevados
    -0.43
     jusque
    -0.43
    Более
    -0.43
     genoux
    -0.43
     totalité
    -0.43
    POSITIVE LOGITS
     types
    1.42
     advantages
    1.24
     Types
    1.24
     characteristics
    1.15
     importance
    1.14
    advantages
    1.08
    types
    1.07
    Types
    1.07
     reasons
    1.03
     TYPES
    1.02
    Activations Density 0.517%

    No Known Activations