© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8165
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to account verification processes

    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
    IVEREF
    -0.56
    webElement
    -0.56
    يون
    -0.55
    話が
    -0.51
    máscara
    -0.50
     يتيمه
    -0.48
     wins
    -0.48
    τός
    -0.48
    spesies
    -0.47
    دانشنامهٔ
    -0.47
    POSITIVE LOGITS
     BorderRadius
    0.67
    adaptiveStyles
    0.59
    ющего
    0.56
    WriteBarrier
    0.54
    AnchorStyles
    0.53
     оригіналу
    0.53
     Reverso
    0.52
    CodeAttribute
    0.52
    Искәрмәләр
    0.51
    ыгана
    0.51
    Activations Density 0.036%

    No Known Activations