Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-GEMMASCOPE-RES-16K
    6. 9744
    Prev
    Next
    INDEX
    Explanations

    sentences expressing confusion or contradiction regarding societal beliefs and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.63
    devamını
    -0.52
     autorytatywna
    -0.51
    SharedCtor
    -0.50
    --}}
    -0.50
    itempty
    -0.50
    SharedDtor
    -0.50
    ṉ
    -0.49
    ufficient
    -0.49
     توس
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.59
     addirittura
    0.43
     etc
    0.41
     usw
    0.40
     inoxydable
    0.39
     persino
    0.38
     milliers
    0.37
    reszcie
    0.36
     hatta
    0.36
     dokonce
    0.36
    Activations Density 0.331%

    No Known Activations