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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 899
    Prev
    Next
    INDEX
    Explanations

    terms related to fundraising and resource allocation

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

    funding and growth enablers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ViewFeatures
    -0.45
    windig
    -0.44
    GEBURTSDATUM
    -0.44
    曖昧さ回避
    -0.40
     يتيمه
    -0.39
    Einzelnachweise
    -0.38
    imanapun
    -0.38
     photos
    -0.36
    IBAction
    -0.35
     hôtels
    -0.35
    POSITIVE LOGITS
    funding
    0.44
    ymce
    0.44
    sustaining
    0.43
     financially
    0.43
     sustenance
    0.42
    grunns
    0.42
    机制
    0.41
     funding
    0.41
    运作
    0.41
     aanwezig
    0.41
    Activations Density 0.015%

    No Known Activations