© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    technical and scientific measurements or concentrations

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

    Lab procedures involving mixtures

    np_acts-logits-general · gemini-2.0-flash

    experimental procedures after "was"

    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
     keber
    -0.55
     considér
    -0.51
     يتيمه
    -0.51
    szön
    -0.50
     cumpri
    -0.50
     durer
    -0.50
     Hiding
    -0.49
     HasFactory
    -0.49
     ottim
    -0.49
     Happening
    -0.48
    POSITIVE LOGITS
     allowed
    0.63
    __':
    0.63
     становника
    0.63
     ContentValues
    0.63
     CURIAM
    0.62
     subjected
    0.60
    erevan
    0.60
     placed
    0.59
     Reverso
    0.59
     incubated
    0.59
    Activations Density 0.986%

    No Known Activations