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. 20-GEMMASCOPE-RES-16K
    6. 15571
    Prev
    Next
    INDEX
    Explanations

    words related to cytokines and cell biology

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

    starting with "Ci" or "Cy"

    np_acts-logits-general · gemini-2.0-flash

    Cyamopsis, ciprofloxacin, cyphers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.70
    XmlAccessorType
    -0.67
    #+#
    -0.66
    DockStyle
    -0.64
    sidemargin
    -0.62
    principalTable
    -0.62
    يكب
    -0.61
     cherchés
    -0.60
    Atsauces
    -0.59
    AntiForgeryToken
    -0.59
    POSITIVE LOGITS
     ci
    0.56
    phers
    0.56
    Gön
    0.54
     Ci
    0.54
    pher
    0.53
    schaft
    0.49
    CrossRef
    0.47
    Ci
    0.46
     secco
    0.46
     confirm
    0.45
    Activations Density 0.119%

    No Known Activations