© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9324
    Prev
    Next
    INDEX
    Explanations

    code related to Java utilities and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     ***!
    -0.61
    ongoose
    -0.51
    EndProject
    -0.51
     Reinforcement
    -0.51
    MessageTagHelper
    -0.49
     princess
    -0.49
    CodeAttribute
    -0.47
     mongoose
    -0.46
     Kugel
    -0.45
    MetaType
    -0.45
    POSITIVE LOGITS
    noinspection
    0.79
    Supplier
    0.65
    supplier
    0.64
     Supplier
    0.63
     RIPRODUZIONE
    0.62
    Suppliers
    0.62
     supplier
    0.60
     auroit
    0.60
     immutable
    0.59
    <>(
    0.58
    Activations Density 0.629%

    No Known Activations