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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6015
    Prev
    Next
    INDEX
    Explanations

    references to 'its' and related possessive forms indicating ownership or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.52
     preferido
    -0.50
     personales
    -0.49
     personalmente
    -0.48
     kaybet
    -0.47
    personal
    -0.47
    py
    -0.47
     pessoal
    -0.45
     Normdatei
    -0.45
     spake
    -0.45
    POSITIVE LOGITS
     its
    0.93
     Its
    0.93
    tvguidetime
    0.91
     ITS
    0.89
     contents
    0.87
    Its
    0.85
    它的
    0.80
    nehå
    0.80
    æus
    0.79
    hould
    0.76
    Activations Density 0.256%

    No Known Activations