Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5821
    Prev
    Next
    INDEX
    Explanations

    actions or events related to violent incidents or altercations

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

    "bed" or "beds"

    np_acts-logits-general · gemini-2.0-flash

    bed, beds, bedroom

    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
     Sociales
    -0.56
     ComVisible
    -0.49
    TagHelpers
    -0.47
     Cigar
    -0.47
     cigar
    -0.45
     Générale
    -0.44
     tán
    -0.44
     HomeController
    -0.44
    jetivos
    -0.43
    MenuInflater
    -0.43
    POSITIVE LOGITS
     bed
    2.27
     beds
    1.85
    bed
    1.77
     Bed
    1.74
    Bed
    1.73
     BED
    1.66
    beds
    1.55
     Beds
    1.54
    BED
    1.46
    Beds
    1.40
    Activations Density 0.115%

    No Known Activations