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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 178
    Prev
    Next
    INDEX
    Explanations

    references to companies and their activities within various industries

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

    corporate and business-related terminology and phrases.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     AssemblyCulture
    -0.40
    canestro
    -0.38
    lijker
    -0.35
     Roskov
    -0.35
     Russian
    -0.35
     Russians
    -0.35
     cu
    -0.35
    gegeben
    -0.34
    ])))
    -0.34
    featureID
    -0.34
    POSITIVE LOGITS
    KommentareTeilen
    0.59
     headquartered
    0.57
     AssemblyTitle
    0.56
     owned
    0.55
    owned
    0.53
     thrived
    0.53
    总部
    0.51
     prosper
    0.51
     company
    0.50
     headquarters
    0.50
    Activations Density 0.155%

    No Known Activations