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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15677
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to progress and achievement

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

    Comes before verbs like "make," "look," "try," "save," "see"

    np_acts-logits-general · gemini-2.0-flash

    make up

    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
    IonicModule
    -0.65
    حوالہ
    -0.63
    Demografie
    -0.61
    Pautan
    -0.57
    ⓧ
    -0.57
     Мексичка
    -0.56
    onames
    -0.53
    ással
    -0.51
     saites
    -0.51
    umesc
    -0.51
    POSITIVE LOGITS
     ולה
    1.19
     ול
    0.95
    脚注の使い方
    0.74
    enumi
    0.73
     oneself
    0.66
    \{\\
    0.65
     further
    0.65
     المعيارى
    0.64
     möglichst
    0.64
     thêm
    0.59
    Activations Density 0.709%

    No Known Activations