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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10216
    Prev
    Next
    INDEX
    Explanations

    actions related to capturing or receiving, particularly in a physical or metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.37
     antaranya
    -0.36
     Reiter
    -0.36
     Schle
    -0.35
    notifyListeners
    -0.35
     ring
    -0.34
     idyllic
    -0.34
     चीज़ों
    -0.33
    +#+
    -0.33
     hero
    -0.33
    POSITIVE LOGITS
     catching
    0.81
    Catch
    0.77
     Catch
    0.75
    catching
    0.75
     catch
    0.71
    catch
    0.70
    CATCH
    0.70
    FOREIGN
    0.69
     CATCH
    0.68
    Catching
    0.68
    Activations Density 1.736%

    No Known Activations