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. 23-GEMMASCOPE-RES-16K
    6. 10365
    Prev
    Next
    INDEX
    Explanations

    phrases related to computing and server connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.72
     дописавши
    -0.62
     iirc
    -0.58
     nė
    -0.52
     елның
    -0.51
    可以说是
    -0.51
    simply
    -0.50
     IIRC
    -0.49
    Simply
    -0.49
     Simplemente
    -0.49
    POSITIVE LOGITS
     blah
    0.96
     XYZ
    0.96
     X
    0.94
    〇〇
    0.93
    ○○
    0.87
     xyz
    0.82
    XYZ
    0.77
    IntoConstraints
    0.76
    !”.
    0.76
     فل
    0.74
    Activations Density 0.296%

    No Known Activations