© 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. 13738
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and suggestions

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

    sequences of actions or processes connected by "and" conjunctions.

    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
    <?
    -0.48
     AssemblyCompany
    -0.43
    lussen
    -0.42
     установлен
    -0.40
     sağlar
    -0.40
     arşivlendi
    -0.40
     добав
    -0.40
     Савезне
    -0.40
    ArrowToggle
    -0.40
     diterapkan
    -0.39
    POSITIVE LOGITS
     making
    1.73
     getting
    1.70
     taking
    1.63
     having
    1.62
     being
    1.58
     putting
    1.58
     creating
    1.55
     bringing
    1.53
     giving
    1.47
     doing
    1.46
    Activations Density 2.694%

    No Known Activations