© 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. 37-GEMMASCOPE-RES-16K
    6. 841
    Prev
    Next
    INDEX
    Explanations

    informal expressions and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.54
    clerView
    -0.50
     itſelf
    -0.45
     pleaſure
    -0.44
    ſelves
    -0.43
     صوتيه
    -0.43
    囗
    -0.42
    talt
    -0.42
     Sábado
    -0.41
    bine
    -0.41
    POSITIVE LOGITS
     men
    0.58
     mem
    0.55
     Men
    0.49
     mens
    0.48
     meng
    0.47
    DoubleQuotes
    0.46
    SharedDtor
    0.46
     meri
    0.46
     AssemblyTitle
    0.45
     beru
    0.44
    Activations Density 0.029%

    No Known Activations