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. 7-GEMMASCOPE-RES-16K
    6. 6050
    Prev
    Next
    INDEX
    Explanations

    references to software installation and configuration errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lượt
    -0.52
    formik
    -0.43
    self
    -0.43
    avadoc
    -0.43
    esgue
    -0.42
    étaient
    -0.40
    #
    -0.40
    GOTREF
    -0.39
    I
    -0.38
    msubsup
    -0.38
    POSITIVE LOGITS
     Monfieur
    0.86
     Jefus
    0.81
     whoſe
    0.80
    MemoryWarning
    0.78
     ſtate
    0.78
     typelib
    0.77
     whofe
    0.77
     himſelf
    0.76
     itſelf
    0.76
     myſelf
    0.76
    Activations Density 0.712%

    No Known Activations