© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords indicating abundance or variety in context

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

    the phrase "a wide variety" or similar expressions indicating diverse categories or applications.

    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
    Grupos
    -0.45
     dép
    -0.44
     tää
    -0.40
     satunya
    -0.39
    (@"%@",
    -0.39
    Gruppen
    -0.38
    CodeAttribute
    -0.38
    Muy
    -0.38
     محفوظة
    -0.36
    hagen
    -0.36
    POSITIVE LOGITS
     variety
    1.09
     number
    0.96
     range
    0.88
    variety
    0.78
     array
    0.73
     assortment
    0.69
     multitude
    0.69
     slew
    0.69
     Vielzahl
    0.66
     wide
    0.66
    Activations Density 0.232%

    No Known Activations