© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2004
    Prev
    Next
    INDEX
    Explanations

    quantifiable structures or sections in a context, such as chapters, channels, or data partitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.62
     المعيارى
    -0.59
     censiti
    -0.54
    ChildScrollView
    -0.50
    homonymie
    -0.48
    NLS
    -0.48
    Бахар
    -0.47
    Rhestr
    -0.47
    XmlAccessType
    -0.47
    SBATCH
    -0.47
    POSITIVE LOGITS
     each
    0.59
     ciasc
    0.51
    each
    0.49
     Each
    0.48
    Each
    0.48
     ciascuno
    0.47
     ognuno
    0.46
     fiecare
    0.45
     chacune
    0.44
     chacun
    0.43
    Activations Density 0.493%

    No Known Activations