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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9270
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to sorting data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Beasley
    -0.73
     glyphicon
    -0.67
    Diam
    -0.66
    Daw
    -0.64
    inquirer
    -0.61
    schlag
    -0.60
    <h4>
    -0.60
    lamino
    -0.59
     deney
    -0.58
    imread
    -0.58
    POSITIVE LOGITS
     SORT
    1.50
     Sorting
    1.38
     Sort
    1.36
    SORT
    1.26
     sorting
    1.22
    Sort
    1.21
     sorts
    1.20
    sorting
    1.17
     sort
    1.10
     sorter
    1.08
    Activations Density 0.069%

    No Known Activations