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. 21-GEMMASCOPE-RES-16K
    6. 13995
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and logic in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PointerException
    -0.72
     RIPRODUZIONE
    -0.72
    Portale
    -0.72
    WebServlet
    -0.72
     confirmer
    -0.71
    ]--;
    -0.71
     mergeFrom
    -0.70
    modifiable
    -0.68
    السكان
    -0.68
    marshaller
    -0.68
    POSITIVE LOGITS
    item
    0.54
    toxicity
    0.52
     referrerpolicy
    0.51
    itemize
    0.51
     baig
    0.48
    umahan
    0.48
    λευ
    0.45
     surla
    0.42
    ItemSelected
    0.40
     الحره
    0.40
    Activations Density 0.017%

    No Known Activations