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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10682
    Prev
    Next
    INDEX
    Explanations

    names of significant individuals and their historical actions

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

    circus or aerial performance

    np_acts-logits-general · gemini-2.0-flash

    circus and aerialist circus performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſta
    -0.56
    PreferredItem
    -0.54
    mbggenerated
    -0.51
     camiset
    -0.50
     increí
    -0.49
     pleaſure
    -0.49
    IsMutable
    -0.49
    bootstrapcdn
    -0.48
    TextWatcher
    -0.48
     defaultstate
    -0.47
    POSITIVE LOGITS
     circus
    0.62
     Circus
    0.58
    Circus
    0.53
    circus
    0.50
     circ
    0.49
     circo
    0.47
     clowns
    0.47
     performance
    0.44
     clown
    0.43
     acrob
    0.43
    Activations Density 0.222%

    No Known Activations