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. 13754
    Prev
    Next
    INDEX
    Explanations

    questions and expressions related to existential uncertainty and reflection

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

    Follows first-person pronouns or possessives

    np_acts-logits-general · gemini-2.0-flash

    writing plainly, in hills, with trust, cloud, suppose, flesh, strong

    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
     EconPapers
    -0.93
     CreateTagHelper
    -0.92
     disambiguazione
    -0.91
    endphp
    -0.90
    \{\\
    -0.89
    writeField
    -0.86
     Autorizaciones
    -0.79
    Autoritní
    -0.78
    verwijspagina
    -0.77
     "..\..\..\
    -0.76
    POSITIVE LOGITS
     magát
    0.46
    下载附件
    0.40
    big
    0.37
     my
    0.37
     ab
    0.37
     förstå
    0.37
    TacToe
    0.36
    signol
    0.36
    日閲覧
    0.36
     medesimo
    0.35
    Activations Density 0.072%

    No Known Activations