© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8228
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations, particularly those related to locations or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     miniaturka
    -0.64
    BibitemShut
    -0.63
    ceğine
    -0.59
    genodigd
    -0.57
    ementara
    -0.57
     größten
    -0.57
     meille
    -0.55
     صوتيه
    -0.55
    lliant
    -0.54
    CONSIN
    -0.54
    POSITIVE LOGITS
    <bos>
    0.61
    .,
    0.56
     Jr
    0.55
    i
    0.51
    Rptr
    0.49
    .;
    0.46
    .(
    0.45
    Mr
    0.45
     مشين
    0.45
    .-
    0.44
    Activations Density 0.371%

    No Known Activations