© 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. 35-GEMMASCOPE-RES-16K
    6. 12789
    Prev
    Next
    INDEX
    Explanations

    instances of the word "specific" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.59
    MessageState
    -0.57
    MessageOf
    -0.56
     /\.
    -0.54
     Wikimedijinoj
    -0.52
    sizeCache
    -0.52
    GEBURTSDATUM
    -0.50
    ISupport
    -0.48
    っぱ
    -0.48
    IndentedString
    -0.47
    POSITIVE LOGITS
    ities
    0.65
     details
    0.49
     circonstances
    0.47
     مرئيه
    0.47
     instance
    0.45
     circumstances
    0.44
     circonst
    0.44
     détails
    0.44
     purpose
    0.44
     aandacht
    0.44
    Activations Density 0.222%

    No Known Activations