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. 2011
    Prev
    Next
    INDEX
    Explanations

    highly valued or positively assessed attributes in a list format

    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
    raisemb
    -0.60
    agaimana
    -0.50
    berdayakan
    -0.48
    Kết
    -0.48
    <?
    -0.47
     VIAF
    -0.46
     Spir
    -0.46
    kloped
    -0.45
    ually
    -0.45
     UnityEditor
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.76
    CodeAttribute
    0.74
     M
    0.71
     الحره
    0.67
     S
    0.65
     J
    0.63
     G
    0.61
     K
    0.60
     P
    0.59
     R
    0.59
    Activations Density 0.188%

    No Known Activations