© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3786
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical concepts related to atmospheric properties and their measurements

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

    "assuming" or "assume"

    np_acts-logits-general · gemini-2.0-flash

    assuming, assumed, assumption

    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
     snippetHide
    -0.59
    otient
    -0.55
    FieldError
    -0.53
     vostri
    -0.52
    หลัก
    -0.52
    crollView
    -0.49
    िखित
    -0.49
    testens
    -0.49
    שְׁ
    -0.49
    displayquote
    -0.49
    POSITIVE LOGITS
     assumption
    1.28
     assumptions
    1.27
     assumed
    1.25
     Assumptions
    1.14
     assume
    1.11
    Assumption
    1.01
    assumption
    0.98
    assumed
    0.98
    Assumptions
    0.98
     Assume
    0.97
    Activations Density 2.044%

    No Known Activations