© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4408
    Prev
    Next
    INDEX
    Explanations

    terms related to systems and concepts of importance and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    क्षित
    -0.36
    HXLINE
    -0.33
    AuthGuard
    -0.31
    高い
    -0.31
     Economist
    -0.30
     femelle
    -0.28
    ícil
    -0.28
    extrême
    -0.28
    ależy
    -0.28
    युक्त
    -0.27
    POSITIVE LOGITS
    isation
    1.16
    ization
    1.15
    ishment
    1.09
    ation
    1.05
    ification
    1.02
    ality
    1.02
    ulation
    1.01
    fication
    1.00
    nement
    1.00
    lessness
    0.98
    Activations Density 0.905%

    No Known Activations