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. 33-GEMMASCOPE-RES-131K
    6. 65922
    Prev
    Next
    INDEX
    Explanations

    references to ad blocking tools and related technology

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sqft
    -0.39
    ViewFeatures
    -0.38
    fficio
    -0.36
    VYMaps
    -0.35
     πό
    -0.33
     پست
    -0.33
    AsUp
    -0.32
     Photocase
    -0.32
    нциклопе
    -0.31
     poste
    -0.31
    POSITIVE LOGITS
     blocking
    0.97
     blocker
    0.83
     blockers
    0.82
     Blocking
    0.81
     blocked
    0.80
     ad
    0.77
    blocking
    0.77
    Blocking
    0.75
    blocker
    0.74
    block
    0.70
    Activations Density 0.046%

    No Known Activations