© 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. 31-GEMMASCOPE-RES-16K
    11. 15831
    Prev
    Next
    INDEX
    Explanations

    specific attributes and details related to product descriptions and framing options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to product dimensions, sizing, and measurements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asted
    -0.32
     departe
    -0.31
    ող
    -0.31
    편
    -0.30
    PyObject
    -0.30
    Diz
    -0.30
    Atle
    -0.28
    atguigu
    -0.28
    keypress
    -0.28
    xcc
    -0.28
    POSITIVE LOGITS
     framed
    1.59
     frame
    1.44
     Frame
    1.30
     Framed
    1.29
    framed
    1.28
     frames
    1.28
     framing
    1.24
    Framed
    1.19
     hanging
    1.18
    Frame
    1.16
    Activations Density 0.136%

    No Known Activations