© 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. 35-GEMMASCOPE-RES-16K
    6. 7039
    Prev
    Next
    INDEX
    Explanations

    elements of musical performance or artistic critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.56
     présidenti
    -0.52
     umana
    -0.51
     navideña
    -0.51
    verständlich
    -0.46
     umane
    -0.45
     exécu
    -0.45
    anyahu
    -0.45
     förslag
    -0.44
     Majefty
    -0.44
    POSITIVE LOGITS
     hipster
    1.35
     hippie
    1.21
     punk
    1.10
     bohemian
    1.08
    punk
    0.93
     cult
    0.92
    hipster
    0.90
     anarchist
    0.90
     geek
    0.89
     goth
    0.89
    Activations Density 0.711%

    No Known Activations