© 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. 13725
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to data structure and JSON formatting

    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
    DebuggerNonUser
    -0.79
     Мексичка
    -0.77
     automatiques
    -0.74
     invokingState
    -0.73
    sidemargin
    -0.72
     дописавши
    -0.72
    lccn
    -0.71
    NameInMap
    -0.70
    SBATCH
    -0.70
     Efq
    -0.70
    POSITIVE LOGITS
    payload
    0.53
     payload
    0.49
     payloads
    0.45
     nội
    0.45
    PerformLayout
    0.44
     artic
    0.43
    RequestBody
    0.42
    agram
    0.40
    hena
    0.40
    optarg
    0.40
    Activations Density 0.323%

    No Known Activations