© 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. 12-GEMMASCOPE-RES-16K
    6. 1340
    Prev
    Next
    INDEX
    Explanations

    references to axes or rotations in mechanical and physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totales
    -0.36
     récord
    -0.35
    Premier
    -0.35
    Risultati
    -0.35
    総
    -0.33
     retr
    -0.33
    Premi
    -0.33
    !
    -0.32
     Premier
    -0.32
    London
    -0.32
    POSITIVE LOGITS
    Axis
    1.52
     axis
    1.52
     Axis
    1.51
     AXIS
    1.40
    axis
    1.40
     Axes
    1.24
    AXIS
    1.23
     axes
    1.15
    軸
    1.14
    轴
    1.09
    Activations Density 0.191%

    No Known Activations