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. 21-GEMMASCOPE-RES-16K
    6. 11793
    Prev
    Next
    INDEX
    Explanations

    references to art institutions and community engagement in the arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avez
    -0.44
    TOUCH
    -0.44
    Бахар
    -0.42
     touché
    -0.42
    Aholisi
    -0.41
    +:+
    -0.41
     논
    -0.40
     Cliquez
    -0.39
     anteriore
    -0.39
    UnusedPrivate
    -0.38
    POSITIVE LOGITS
     artists
    0.49
     houſe
    0.47
     Houſe
    0.47
     gynhyrchwyd
    0.44
     Artists
    0.44
    nextLine
    0.43
     invitations
    0.43
     Eſ
    0.43
     slate
    0.43
    Artist
    0.42
    Activations Density 0.214%

    No Known Activations