© 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. 7-GEMMASCOPE-RES-16K
    6. 6464
    Prev
    Next
    INDEX
    Explanations

    references to time periods and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dostupné
    -0.58
    apimachinery
    -0.57
    inine
    -0.56
     Minden
    -0.53
     propOrder
    -0.52
    antasy
    -0.52
    posals
    -0.51
    énario
    -0.51
     fathom
    -0.49
    xlarge
    -0.49
    POSITIVE LOGITS
     During
    1.23
    During
    1.20
     during
    1.17
     periods
    1.15
    during
    1.14
    Während
    1.07
     period
    1.01
     दौरान
    1.00
    durante
    0.99
    期间
    0.99
    Activations Density 0.221%

    No Known Activations