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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2114
    Prev
    Next
    INDEX
    Explanations

    various perspectives and viewpoints articulated throughout the text

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

    "...perspective" or point of view

    np_acts-logits-general · gemini-2.0-flash

    viewpoint or standpoint

    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
    adaptiveStyles
    -0.53
    勉
    -0.53
     endwhile
    -0.53
    StoryboardSegue
    -0.52
    gwt
    -0.51
     InputDecoration
    -0.51
    ierr
    -0.51
    ̀nh
    -0.50
     Baillargeon
    -0.50
    ellón
    -0.49
    POSITIVE LOGITS
     perspective
    2.57
     perspectives
    2.10
     viewpoint
    2.08
    perspective
    2.06
     standpoint
    1.99
     Perspective
    1.96
     perspectiva
    1.87
     viewpoints
    1.73
     PERSPECT
    1.71
    Perspective
    1.68
    Activations Density 0.225%

    No Known Activations