Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3163
    Prev
    Next
    INDEX
    Explanations

    causal connections and conditions that influence outcomes or events

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

    Follows the word "Since"

    np_acts-logits-general · gemini-2.0-flash

    introducing explanations

    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
    ValueStyle
    -0.60
    hasMoreElements
    -0.58
    addContainerGap
    -0.57
    ровок
    -0.56
    édrale
    -0.56
    urop
    -0.54
    vateľov
    -0.54
     addirittura
    -0.54
     SEDS
    -0.53
    wikidata
    -0.53
    POSITIVE LOGITS
    ########.
    0.68
    发表于
    0.55
    ^(@)
    0.52
    styleType
    0.51
    ंदीखरीदारी
    0.51
    addCriterion
    0.50
    TagHelper
    0.50
     onAnimation
    0.50
     foundation
    0.50
    WebElementEntity
    0.50
    Activations Density 0.213%

    No Known Activations