© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3868
    Prev
    Next
    INDEX
    Explanations

    phrases related to configuring, modifying, or interacting with items and views within a charting or layout context

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

    Tokens preceding actions or functions

    np_acts-logits-general · gemini-2.0-flash

    action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.80
    ьаж
    -0.71
    SequentialGroup
    -0.70
    PreferredItem
    -0.70
    BitmapFactory
    -0.68
    windowFixed
    -0.68
    onAttach
    -0.65
    EndInit
    -0.64
    KommentareTeilen
    -0.63
    orianCalendar
    -0.62
    POSITIVE LOGITS
    此次
    0.54
     shall
    0.53
    feest
    0.52
     action
    0.52
     want
    0.52
     test
    0.52
     Aufmerksamkeit
    0.51
     действие
    0.51
     impact
    0.51
    }());
    0.50
    Activations Density 0.227%

    No Known Activations