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. 10998
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dependencies and relationships between individuals or entities

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

    "rely" or needing help

    np_acts-logits-general · gemini-2.0-flash

    rely on or look to

    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
     coexistence
    -0.54
    stateProvider
    -0.53
     Pfa
    -0.52
    lím
    -0.50
    OrBuilder
    -0.48
     pama
    -0.47
    CompoundButton
    -0.47
    DETECT
    -0.46
    <thead>
    -0.46
    oneofs
    -0.46
    POSITIVE LOGITS
     rely
    1.52
     recurrir
    1.42
     reliance
    1.41
     recourse
    1.38
     relied
    1.36
     relying
    1.36
     relies
    1.29
     Rely
    1.29
     resort
    1.26
     recours
    1.17
    Activations Density 0.285%

    No Known Activations