© 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. 20-GEMMASCOPE-RES-16K
    11. 7987
    Prev
    Next
    INDEX
    Explanations

    technical terminology and methods related to research and experimentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases about methods, techniques, or ways to accomplish tasks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    tonode
    -0.49
    EndContext
    -0.47
    SBATCH
    -0.39
    ContentAlignment
    -0.38
    titleLabel
    -0.37
    endphp
    -0.36
     hanem
    -0.36
     scienza
    -0.36
    AntiForgeryToken
    -0.36
    Einsatz
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.57
     للمعارف
    0.54
    RTGC
    0.53
     CreateTagHelper
    0.48
    InjectAttribute
    0.46
    Knife
    0.45
    dre
    0.42
    RTEE
    0.41
    acchar
    0.41
    OGND
    0.41
    Activations Density 0.506%

    No Known Activations