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. 12456
    Prev
    Next
    INDEX
    Explanations

    references to social accountability or critique

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

    Follows words expressing opinions or stances

    np_acts-logits-general · gemini-2.0-flash

    stand their ground

    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
    windowFixed
    -0.65
     Reverso
    -0.59
    وصلات
    -0.57
    ьаж
    -0.57
    NameInMap
    -0.56
     jScrollPane
    -0.53
    WebServlet
    -0.53
     wireType
    -0.52
    WindowConstants
    -0.52
    Personendaten
    -0.51
    POSITIVE LOGITS
     stand
    1.29
    Stand
    1.22
     standing
    1.18
     Stand
    1.18
     stood
    1.15
     STAND
    1.14
    STAND
    1.13
    stand
    1.11
    Standing
    1.08
     stands
    1.05
    Activations Density 0.294%

    No Known Activations