© 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. 11-GEMMASCOPE-RES-16K
    6. 1730
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the condition and features of a vehicle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SizeF
    -0.63
    ellschaft
    -0.63
     cancelación
    -0.60
     dépens
    -0.58
     habitudes
    -0.56
    sima
    -0.56
    NOPQRST
    -0.56
    mployed
    -0.55
     matematika
    -0.54
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
    ebay
    0.69
    audiovisuel
    0.59
     vintage
    0.58
     salvage
    0.57
     salvaged
    0.56
     Vintage
    0.55
     condition
    0.54
     inherited
    0.54
    Vintage
    0.54
     restored
    0.52
    Activations Density 0.138%

    No Known Activations