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. 25-GEMMASCOPE-RES-16K
    6. 3833
    Prev
    Next
    INDEX
    Explanations

    code structure and programming syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.57
    StoreMessageInfo
    -0.51
    saraba
    -0.51
    erover
    -0.51
     cherchés
    -0.49
    usercontent
    -0.49
     HasFactory
    -0.49
    indd
    -0.49
    Controllo
    -0.46
    googleapis
    -0.44
    POSITIVE LOGITS
    RRect
    0.52
    !*\
    0.52
    ایای
    0.50
     gaze
    0.48
    ]='\
    0.48
    zzles
    0.48
    rupal
    0.47
     PyTuple
    0.47
    obic
    0.46
    ípios
    0.46
    Activations Density 0.069%

    No Known Activations