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. 24-GEMMASCOPE-RES-16K
    6. 14167
    Prev
    Next
    INDEX
    Explanations

    references to priestly duties and regulations related to the tribe of Levi

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

    religious rituals or offerings

    np_acts-logits-general · gemini-2.0-flash

    religious sacrifices and rituals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trait
    -0.51
     ressort
    -0.48
    ScopeManager
    -0.47
    parseDouble
    -0.47
    ukų
    -0.46
    enterOuterAlt
    -0.46
    UnknownFieldSet
    -0.46
     Thessal
    -0.44
    ApiModel
    -0.42
     Hik
    -0.42
    POSITIVE LOGITS
     sacrifice
    1.30
     ritual
    1.29
     sacrifices
    1.24
     ceremonies
    1.18
     ceremony
    1.16
     rituals
    1.14
     Sacrifice
    1.14
     sacrificial
    1.14
     ceremonial
    1.13
     sacrificed
    1.12
    Activations Density 0.286%

    No Known Activations