Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12788
    Prev
    Next
    INDEX
    Explanations

    instances of action phrases or directives involving movement or location

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

    Prepositions followed by locations

    np_acts-logits-general · gemini-2.0-flash

    to school, to bed, to jail

    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
     ffilm
    -0.69
     Itself
    -0.61
    czegó
    -0.57
     invokingState
    -0.55
    رشف
    -0.55
     recevez
    -0.53
     linkovi
    -0.53
    endcsname
    -0.52
    AnchorStyles
    -0.52
    ?}",
    -0.52
    POSITIVE LOGITS
     school
    1.11
     church
    1.02
     town
    0.99
     bed
    0.94
     court
    0.90
     work
    0.86
     class
    0.80
     college
    0.80
     camp
    0.79
    school
    0.78
    Activations Density 0.450%

    No Known Activations