© 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. 4-GEMMASCOPE-RES-16K
    11. 372
    Prev
    Next
    INDEX
    Explanations

    terms related to patents and disclosures of scientific or technical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ['./
    -0.62
    脚注の使い方
    -0.62
    anovich
    -0.57
     mijne
    -0.54
    FXML
    -0.54
    parsedMessage
    -0.53
    dorff
    -0.51
    GraphicsUnit
    -0.50
    haustible
    -0.50
    /**
    -0.49
    POSITIVE LOGITS
    ForValue
    0.66
    InjectAttribute
    0.65
    AndEndTag
    0.65
    IUrlHelper
    0.60
    RegressionTest
    0.58
     déput
    0.55
    <bos>
    0.55
    }{*}{
    0.55
     CreateTagHelper
    0.55
     Autónoma
    0.55
    Activations Density 1.078%

    No Known Activations