© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4951
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate merging, combining, or blending of concepts or themes

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

    phrases that combine or blend different concepts or 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
     confronti
    -0.40
    etc
    -0.40
     kasarigan
    -0.37
     etc
    -0.35
    AppComponent
    -0.35
    ])->
    -0.35
     canst
    -0.35
     refor
    -0.33
     proszę
    -0.32
     consci
    -0.32
    POSITIVE LOGITS
     combining
    0.72
    Combining
    0.69
     Combining
    0.68
     blending
    0.68
     combines
    0.68
    ftagPool
    0.66
     between
    0.65
     blend
    0.63
     blends
    0.63
    spaceBetween
    0.62
    Activations Density 0.302%

    No Known Activations