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. 16-GEMMASCOPE-RES-16K
    6. 12879
    Prev
    Next
    INDEX
    Explanations

    specific technical aspects related to mechanical and structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.70
    ⓧ
    -0.58
     ModelExpression
    -0.55
    ValueStyle
    -0.53
    DockStyle
    -0.52
    Tembelea
    -0.52
    httphttps
    -0.52
    
    -0.51
    UserScript
    -0.51
    AndEndTag
    -0.49
    POSITIVE LOGITS
     mesh
    0.54
     espiral
    0.49
    Mesh
    0.48
     Mesh
    0.46
    mesh
    0.45
     ogrod
    0.44
     сет
    0.44
     ladder
    0.42
     maille
    0.41
    hysema
    0.40
    Activations Density 0.492%

    No Known Activations