© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15867
    Prev
    Next
    INDEX
    Explanations

    references to educational resources and user demographics in the context of online platforms and community interactions

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

    People/entities "looking" or "wanting"

    np_acts-logits-general · gemini-2.0-flash

    groups looking for

    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
    AddTagHelper
    -0.78
    PrototypeOf
    -0.58
    labelledby
    -0.56
    printLine
    -0.54
    Portail
    -0.50
    parency
    -0.48
     strconv
    -0.47
     Childhood
    -0.47
    IndentedString
    -0.46
    ModelAdmin
    -0.46
    POSITIVE LOGITS
     looking
    1.60
     wanting
    1.58
     wishing
    1.53
     desiring
    1.39
     interested
    1.38
     seeking
    1.35
    looking
    1.16
     hoping
    1.12
     LOOKING
    1.11
     desirous
    1.11
    Activations Density 0.192%

    No Known Activations