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. 19-GEMMASCOPE-RES-16K
    6. 15826
    Prev
    Next
    INDEX
    Explanations

    lines of code that contain escape sequences or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jší
    -0.49
     sm
    -0.44
     a
    -0.43
    tion
    -0.43
     ką
    -0.43
    /$',
    -0.43
    <<"\
    -0.43
     Spa
    -0.43
    uch
    -0.42
     Sp
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.83
     calendriers
    0.80
     Shakspeare
    0.78
     Cæsar
    0.78
    setArguments
    0.77
     محفوظة
    0.77
    RectangleBorder
    0.77
     متعلقه
    0.75
    GraphicsUnit
    0.74
     Sarm
    0.72
    Activations Density 0.083%

    No Known Activations