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. 16-GEMMASCOPE-RES-16K
    6. 6020
    Prev
    Next
    INDEX
    Explanations

    terms related to changing or transitioning states, especially regarding technology or personal focus

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

    changing or transferring

    np_acts-logits-general · gemini-2.0-flash

    switching to or from options

    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
    +:+
    -0.48
    tilhe
    -0.45
    semver
    -0.45
    ReadKey
    -0.44
    itian
    -0.44
    PhysRevD
    -0.43
    allible
    -0.43
     truth
    -0.43
    loroethene
    -0.43
     defStyleAttr
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.96
     nahilalakip
    0.83
     Савезне
    0.76
     swit
    0.75
    shift
    0.74
     into
    0.74
     shift
    0.73
     switch
    0.73
    contentLoaded
    0.73
    switchTo
    0.72
    Activations Density 0.307%

    No Known Activations