Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14887
    Prev
    Next
    INDEX
    Explanations

    instances of establishment, founding, or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.50
    Nemo
    -0.46
     convertView
    -0.45
    Carex
    -0.45
    SwitchCompat
    -0.44
     MotionEvent
    -0.44
     getItemCount
    -0.44
     serangga
    -0.44
     Nemo
    -0.43
    ürk
    -0.43
    POSITIVE LOGITS
     foundation
    0.91
     FOUNDATION
    0.87
     Foundation
    0.81
    Foundation
    0.80
     fondation
    0.80
    foundation
    0.78
     fundación
    0.77
     Foundations
    0.74
    Foundations
    0.72
     ESTABL
    0.72
    Activations Density 0.163%

    No Known Activations