© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 527
    Prev
    Next
    INDEX
    Explanations

    terms related to earthquake measurement scales and their descriptions

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

    terms related to seismic activity and earthquakes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and terms related to seismology and earthquakes.

    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
     defaultstate
    -0.46
     springfox
    -0.37
    ValueGenerated
    -0.35
     jagung
    -0.35
     cappuccio
    -0.34
     Maciej
    -0.32
     puissiez
    -0.30
    inx
    -0.29
    נְ
    -0.29
    意
    -0.29
    POSITIVE LOGITS
     earthquake
    1.77
     earthquakes
    1.55
    Earthquake
    1.51
     quake
    1.46
     Earthquake
    1.45
     seismic
    1.44
     Earthquakes
    1.29
     seismo
    1.28
     Seismic
    1.27
    quake
    1.27
    Activations Density 0.134%

    No Known Activations