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. 8050
    Prev
    Next
    INDEX
    Explanations

    Specific geographic locations and property details related to real estate listings

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

    before locations or names

    np_acts-logits-general · gemini-2.0-flash

    locations and specific entities

    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
    —“
    -0.68
    Климат
    -0.68
    MethodManager
    -0.67
    ,’”
    -0.66
    Бахар
    -0.65
    )]=
    -0.63
    ),”
    -0.63
    >");
    
    -0.63
    ?”
    -0.63
    !”
    -0.62
    POSITIVE LOGITS
     undefined
    0.77
     ,.
    0.75
     (,
    0.73
     ().
    0.70
     -.
    0.69
     -,
    0.67
     Other
    0.67
     Unknown
    0.67
    undefined
    0.67
     ,
    0.65
    Activations Density 0.335%

    No Known Activations