© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and expressions used to shift the focus of the discussion or narrative

    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
    RegistryLite
    -0.64
    NewUrlParser
    -0.62
    LabelTagHelper
    -0.61
    twimg
    -0.59
    ########.
    -0.57
     snippetHide
    -0.57
    hyrchwyd
    -0.54
    LayoutStyle
    -0.54
    "]))
    -0.54
    AddTagHelper
    -0.53
    POSITIVE LOGITS
    Anyway
    0.75
     Anyway
    0.71
     Anyways
    0.69
    Anyways
    0.69
    Anyhow
    0.65
     meanwhile
    0.65
    anmoins
    0.64
    BTW
    0.64
     Nevertheless
    0.60
     nevertheless
    0.59
    Activations Density 0.340%

    No Known Activations