© 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. 34-GEMMASCOPE-RES-16K
    11. 11564
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and conditions related to existence and properties within a defined set

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bigoplus
    -0.52
    الحياه
    -0.44
    rungsseite
    -0.44
    Essential
    -0.42
    +#+#
    -0.42
    Essentially
    -0.40
    jména
    -0.40
     addTo
    -0.40
    oplus
    -0.39
    ipers
    -0.39
    POSITIVE LOGITS
     such
    1.19
    such
    0.99
     satisfying
    0.78
     SUCH
    0.77
     Such
    0.77
    Such
    0.72
     ſuch
    0.69
    使得
    0.68
     satisfy
    0.67
     sådan
    0.67
    Activations Density 2.025%

    No Known Activations