Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11417
    Prev
    Next
    INDEX
    Explanations

    statements expressing opinions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.51
    enterOuterAlt
    -0.50
     kohdetta
    -0.48
    лтемелер
    -0.45
     fieldNum
    -0.41
     parseFrom
    -0.40
     دیکھیے
    -0.39
    oriques
    -0.39
    ungguh
    -0.37
    fromnode
    -0.36
    POSITIVE LOGITS
     better
    3.11
    better
    2.84
    Better
    2.72
     Better
    2.61
     mejor
    2.59
     лучше
    2.34
     melhor
    2.33
     BETTER
    2.25
     meglio
    2.25
     mieux
    2.20
    Activations Density 0.637%

    No Known Activations