© 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. 16206
    Prev
    Next
    INDEX
    Explanations

    terms related to reliability and trustworthiness

    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
     GenerationType
    -0.74
    '])){
    -0.65
    cifix
    -0.61
    Nowhere
    -0.60
    rophes
    -0.59
    weird
    -0.59
    setDo
    -0.58
    例句
    -0.57
    IBAction
    -0.57
    FXML
    -0.56
    POSITIVE LOGITS
     reliable
    1.56
     durable
    1.40
    Reliable
    1.36
     Reliable
    1.30
    reliable
    1.27
     dependable
    1.24
     Durable
    1.17
     reliably
    1.12
     trustworthy
    1.12
     zuverläs
    1.11
    Activations Density 0.139%

    No Known Activations