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. 10225
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and their corresponding code functionality

    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
    ["
    -0.52
    of
    -0.44
     
    -0.44
    raš
    -0.43
     .
    -0.43
    ['
    -0.43
    {
    -0.41
     même
    -0.41
    の
    -0.40
    is
    -0.39
    POSITIVE LOGITS
     Efq
    1.24
     CreateTagHelper
    1.22
    ंदीखरीदारी
    1.07
     doubtnut
    1.03
    writeFieldEnd
    1.03
    ContentAsync
    1.00
    DockStyle
    1.00
     myſelf
    0.99
     ―――――
    0.98
     Houſe
    0.98
    Activations Density 0.208%

    No Known Activations