© 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. 34-GEMMASCOPE-RES-16K
    6. 10600
    Prev
    Next
    INDEX
    Explanations

    conversations and discussions about technical processes and patches in programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contando
    -0.47
     consisted
    -0.46
     mostrando
    -0.45
    Hochspringen
    -0.45
     weren
    -0.44
    摇了摇头
    -0.43
     indicando
    -0.42
    zwungen
    -0.40
     tocando
    -0.40
     szüks
    -0.40
    POSITIVE LOGITS
     takes
    1.35
     gets
    1.33
     makes
    1.23
     goes
    1.20
     gives
    1.18
     puts
    1.16
     sends
    1.15
     develops
    1.14
     performs
    1.13
     receives
    1.13
    Activations Density 3.181%

    No Known Activations