© 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. 1294
    Prev
    Next
    INDEX
    Explanations

    terminology related to electronic and nuclear systems

    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
     تضيفلها
    -1.17
     CreateTagHelper
    -1.08
     Sphinx
    -1.02
     Quis
    -0.93
     Xunit
    -0.93
     isComment
    -0.93
     Argonne
    -0.91
     MessageType
    -0.91
    Datuak
    -0.90
     SEK
    -0.89
    POSITIVE LOGITS
    ので
    0.85
    </i>
    0.81
     Woodward
    0.73
     rom
    0.70
    
    0.69
    WithFormat
    0.66
    </em>
    0.66
    osus
    0.66
    jib
    0.65
    </b>
    0.65
    Activations Density 0.800%

    No Known Activations