© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8950
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistics related to economic impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.61
    IsContent
    -0.60
     surla
    -0.56
     jsPsych
    -0.55
     mergeFrom
    -0.54
     FontWeight
    -0.53
    Välislingid
    -0.53
    Activités
    -0.51
     nawr
    -0.51
     Baillargeon
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.85
    Portale
    0.65
     Theſe
    0.57
    ("{}
    0.56
    خصة
    0.54
    Geplaatst
    0.52
     <<<<<<<<<<<<<<
    0.52
     himſelf
    0.52
     houſe
    0.51
    Casi
    0.51
    Activations Density 0.503%

    No Known Activations