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. 4388
    Prev
    Next
    INDEX
    Explanations

    commands or phrases related to taking actions or responsibilities

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

    "Take" followed by an abstract noun

    np_acts-logits-general · gemini-2.0-flash

    take advantage or responsibility

    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
     незавершена
    -0.58
    rdı
    -0.54
     että
    -0.51
    Portály
    -0.51
    Extinguishing
    -0.49
    #
    -0.49
    Schemes
    -0.48
    sizeCache
    -0.47
    </table>
    -0.47
    críbete
    -0.46
    POSITIVE LOGITS
     advantage
    1.44
     care
    1.36
    advantage
    1.05
     aback
    0.88
     charge
    0.88
     note
    0.88
     away
    0.85
     Care
    0.85
     revanche
    0.83
     place
    0.81
    Activations Density 0.163%

    No Known Activations