© 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. 15-GEMMASCOPE-RES-16K
    6. 2689
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and access to resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.54
    ypress
    -0.49
    InternalFrame
    -0.47
     nombreux
    -0.46
    Shear
    -0.44
    estad
    -0.44
     Dominus
    -0.42
     nombreuses
    -0.42
     >=",
    -0.42
    큼
    -0.41
    POSITIVE LOGITS
     only
    1.42
    only
    1.31
     jedynie
    1.23
     seulement
    1.21
    Only
    1.17
     Only
    1.15
     lediglich
    1.12
    而已
    1.11
     лишь
    1.07
    ONLY
    1.04
    Activations Density 0.603%

    No Known Activations