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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5886
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific conditions related to biochemical processes and medical treatments

    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
     nonUne
    -0.54
     resourceCulture
    -0.51
     ſte
    -0.47
     enfans
    -0.47
     ſtre
    -0.47
     deſt
    -0.47
     ſch
    -0.46
    vacy
    -0.46
    ództ
    -0.46
    hæng
    -0.45
    POSITIVE LOGITS
     SwitchCompat
    0.41
    ukone
    0.39
    Autoritní
    0.38
     поход
    0.36
    ResponseWriter
    0.35
    jsdelivr
    0.35
    enderror
    0.35
    ismet
    0.34
    endforeach
    0.34
    VersionUID
    0.33
    Activations Density 2.596%

    No Known Activations