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
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 116
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and real estate development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cru
    -0.34
     आस
    -0.33
     billions
    -0.31
    ィ
    -0.31
     za
    -0.30
     easy
    -0.30
     séries
    -0.29
     én
    -0.29
     My
    -0.28
    My
    -0.28
    POSITIVE LOGITS
     queſta
    0.81
     Autorizaciones
    0.75
    Tikang
    0.74
    IVEREF
    0.71
    .*")]
    0.71
     Chwiliwch
    0.70
     imagui
    0.68
    uxxxx
    0.66
    PreferredItem
    0.66
     メンテナ
    0.66
    Activations Density 0.008%

    No Known Activations