© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 14133
    Prev
    Next
    INDEX
    Explanations

    connections to specific products or solutions related to functionality and performance

    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
    excellents
    -0.52
     esetén
    -0.51
    among
    -0.46
     ujednoznacz
    -0.46
     publiques
    -0.46
     élevées
    -0.42
    guous
    -0.42
     rime
    -0.42
    lizabeth
    -0.42
    cares
    -0.42
    POSITIVE LOGITS
     itself
    0.98
    itself
    0.81
     Itself
    0.76
    CrossRef
    0.73
    SBATCH
    0.72
    ]")]
    0.70
     autorytatywna
    0.70
    SharedCtor
    0.69
     insuffisamment
    0.69
     onAnimation
    0.69
    Activations Density 1.177%

    No Known Activations