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. 237
    Prev
    Next
    INDEX
    Explanations

    terms related to microbial processes or experimentation methodologies

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

    technical/scientific terminology related to laboratory procedures and experimental methods.

    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
    ьаж
    -0.47
     Schild
    -0.44
    fastjson
    -0.43
     AssemblyTitle
    -0.42
    sweetalert
    -0.42
     DISTR
    -0.38
    Atoi
    -0.38
    occasione
    -0.38
     dist
    -0.38
     sweetest
    -0.38
    POSITIVE LOGITS
    ReusableCell
    0.51
    الحياه
    0.51
     filtration
    0.47
    CPtr
    0.46
     initWithFrame
    0.44
    featureID
    0.42
     وتسجيلات
    0.42
    elts
    0.42
    filtration
    0.41
    Datuak
    0.41
    Activations Density 0.543%

    No Known Activations