© 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. 6370
    Prev
    Next
    INDEX
    Explanations

    elements related to data organization and survey methodologies

    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
    prot
    -0.40
    StoryboardSegue
    -0.40
    PROT
    -0.38
     Protector
    -0.37
     Prince
    -0.36
    platz
    -0.36
    Prince
    -0.35
    fycat
    -0.33
    plätze
    -0.33
    godic
    -0.32
    POSITIVE LOGITS
     panel
    3.22
     Panel
    2.86
     panels
    2.80
    panel
    2.72
     PANEL
    2.63
    Panel
    2.56
     Panels
    2.50
    PANEL
    2.39
     paneles
    2.33
    panels
    2.28
    Activations Density 0.588%

    No Known Activations