© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4421
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to HTML or XML formatting in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML and web page structure elements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.65
    ]")]
    -0.57
     lazos
    -0.53
    Personendaten
    -0.53
     increí
    -0.52
     iprot
    -0.50
     Biôgrafia
    -0.50
    PerformLayout
    -0.48
     desmotivaciones
    -0.47
     незавершена
    -0.47
    POSITIVE LOGITS
    ParallelGroup
    0.50
     Including
    0.45
     Half
    0.45
     including
    0.43
    BeginContext
    0.43
     &___
    0.42
     Several
    0.42
     Marshall
    0.42
    Including
    0.41
     Without
    0.39
    Activations Density 0.088%

    No Known Activations