© 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. 33-GEMMASCOPE-RES-16K
    6. 11954
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and support networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     henvisninger
    -0.46
    amerikanischer
    -0.43
    SBATCH
    -0.42
     IQ
    -0.40
    ListItemIcon
    -0.39
     unggul
    -0.39
    ValueStyle
    -0.39
     especializado
    -0.38
     مشارکت‌کنندگان
    -0.38
     bege
    -0.37
    POSITIVE LOGITS
     autobio
    1.20
     candid
    1.16
     honesty
    1.13
     honest
    1.10
     introspection
    1.02
     frank
    1.01
     autobiography
    0.98
     confessions
    0.95
     truthful
    0.93
    honest
    0.92
    Activations Density 0.399%

    No Known Activations