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. 3-GEMMASCOPE-RES-16K
    6. 8037
    Prev
    Next
    INDEX
    Explanations

    references to architectural features and historical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -1.15
     дописавши
    -1.14
    UserScript
    -1.09
    AddTagHelper
    -1.09
     Signalez
    -1.00
     houſe
    -0.99
    脚注の使い方
    -0.95
    évaluateur
    -0.94
    NUMX
    -0.94
     betweenstory
    -0.94
    POSITIVE LOGITS
     statue
    0.63
     logo
    0.63
     sculpture
    0.52
    ></
    0.52
     sign
    0.51
     Sculpture
    0.49
     symbol
    0.48
     Sign
    0.48
     statues
    0.48
     SIGN
    0.47
    Activations Density 0.397%

    No Known Activations