© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    references to beds and related furniture

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

    "bed" or related terms

    np_acts-logits-general · gemini-2.0-flash

    bed, bedding, bedclothes

    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
     متعلقه
    -0.74
    tvguidetime
    -0.71
    MemoryWarning
    -0.67
     AssemblyCulture
    -0.60
    eability
    -0.59
    AxisAlignment
    -0.58
    ViewFeatures
    -0.57
    CROSSTALK
    -0.57
    homonymie
    -0.56
     StringTokenizer
    -0.55
    POSITIVE LOGITS
     Bed
    0.73
    sheets
    0.72
    chamber
    0.72
    ridden
    0.71
    Bed
    0.71
     Beds
    0.69
     sheets
    0.68
     linens
    0.67
    ouin
    0.66
    Beds
    0.65
    Activations Density 0.075%

    No Known Activations