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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8419
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical descriptions, particularly in relation to plant or biological characteristics and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.57
    NameInMap
    -0.48
     AssemblyVersion
    -0.45
    ValueStyle
    -0.43
     resourceCulture
    -0.43
    Carriera
    -0.42
    Personendaten
    -0.42
    DllImport
    -0.41
     etc
    -0.40
    पया
    -0.40
    POSITIVE LOGITS
    ſelf
    0.46
    tagHelperRunner
    0.44
    ➌
    0.41
    ofire
    0.41
     defaultstate
    0.41
     Redesign
    0.41
     Pigment
    0.41
     houſe
    0.39
    Itoa
    0.39
    Spolja
    0.39
    Activations Density 0.239%

    No Known Activations