© 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. 5165
    Prev
    Next
    INDEX
    Explanations

    phrases that identify a problem or question and discuss potential solutions

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

    phrases where "problem" or "question" introduces a challenge or issue to be addressed.

    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
     arşivlendi
    -0.79
    OGND
    -0.79
     незавершена
    -0.60
    URLException
    -0.56
     Normdatei
    -0.55
    ChildScrollView
    -0.54
    bulaire
    -0.54
    orsese
    -0.52
     resultList
    -0.52
     whiteColor
    -0.52
    POSITIVE LOGITS
     being
    0.52
     here
    0.49
     hierbei
    0.42
    RenderAtEndOf
    0.41
    Being
    0.39
     is
    0.39
     daarbij
    0.37
     therein
    0.36
     always
    0.36
    being
    0.36
    Activations Density 0.319%

    No Known Activations