© 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. 20-GEMMASCOPE-RES-16K
    11. 305
    Prev
    Next
    INDEX
    Explanations

    references to customer service and support in product descriptions

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    will or to followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.65
     referenties
    -0.53
     isInitialized
    -0.51
    TestingModule
    -0.49
     Initialized
    -0.48
    envol
    -0.47
    mybatisplus
    -0.47
    espé
    -0.47
    Autoritní
    -0.46
    вере
    -0.46
    POSITIVE LOGITS
    ineno
    0.70
    новниш
    0.60
    osovo
    0.54
    haustible
    0.54
    twimg
    0.53
    toise
    0.53
     videre
    0.53
     مواليد
    0.52
    FTFY
    0.52
    nologue
    0.51
    Activations Density 0.355%

    No Known Activations