© 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. 16098
    Prev
    Next
    INDEX
    Explanations

    prepositions and their frequency of occurrence

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

    "In" preceding a noun

    np_acts-logits-general · gemini-2.0-flash

    in followed by state or status

    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
    setVerticalGroup
    -0.67
    ThroughAttribute
    -0.59
     présidenti
    -0.55
     amitié
    -0.54
    resave
    -0.54
     dignité
    -0.53
    standers
    -0.52
    IVEREF
    -0.52
    HomeAsUpEnabled
    -0.52
    LookAnd
    -0.52
    POSITIVE LOGITS
     play
    1.38
     use
    1.10
     existence
    0.98
     operation
    0.96
    play
    0.94
     place
    0.92
     focus
    0.92
     circulation
    0.92
     question
    0.88
     effect
    0.88
    Activations Density 0.270%

    No Known Activations