© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 15699
    Prev
    Next
    INDEX
    Explanations

    elements related to database queries and user interactions in programming contexts

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

    Mentions "user" or "users"

    np_acts-logits-general · gemini-2.0-flash

    user, users

    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
    Tē
    -0.65
    XmlAccessType
    -0.56
     المعيارى
    -0.52
     kaynağından
    -0.51
    Abitanti
    -0.51
    TagHelper
    -0.49
    دانشنامهٔ
    -0.48
    oa̍t
    -0.48
     propOrder
    -0.47
     invokingState
    -0.47
    POSITIVE LOGITS
     user
    3.66
    user
    3.29
     User
    2.94
    User
    2.79
     users
    2.71
     USER
    2.49
    USER
    2.40
     Users
    2.29
    用户
    2.21
    users
    2.19
    Activations Density 0.161%

    No Known Activations