© 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. 12076
    Prev
    Next
    INDEX
    Explanations

    information related to research and development of interventions in various fields

    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
     فريبيس
    -0.56
    aarrggbb
    -0.55
    SequentialGroup
    -0.55
     للاسماء
    -0.52
    CppMethod
    -0.52
    \{\\
    -0.52
    qrstuvwxyz
    -0.51
    ChildScrollView
    -0.49
    Портали
    -0.48
    couvrez
    -0.48
    POSITIVE LOGITS
     planning
    0.80
     informed
    0.78
     guide
    0.77
     decision
    0.75
     understanding
    0.73
     decisions
    0.71
     guiding
    0.68
     inform
    0.66
     better
    0.66
     guides
    0.65
    Activations Density 0.890%

    No Known Activations