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. 1-GEMMASCOPE-RES-16K
    6. 9653
    Prev
    Next
    INDEX
    Explanations

    structural elements and syntax in textual content, particularly in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.58
    <?
    -0.56
    ImageContext
    -0.56
    zustellen
    -0.52
    didSet
    -0.51
    — 
    -0.50
    pédie
    -0.50
    crapers
    -0.49
    vdots
    -0.49
    grà
    -0.47
    POSITIVE LOGITS
    SpringBootTest
    0.76
    cshtml
    0.74
     poffe
    0.71
     Houſe
    0.69
     Majefty
    0.68
     nargin
    0.65
     purpoſe
    0.65
     firſt
    0.64
    parsedMessage
    0.64
     Chriftian
    0.63
    Activations Density 0.871%

    No Known Activations