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. 17-GEMMASCOPE-RES-16K
    6. 5238
    Prev
    Next
    INDEX
    Explanations

    technical language related to patent applications and compositions for medical treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.77
    Personensuche
    -0.74
     صوتيه
    -0.71
    脚注の使い方
    -0.69
    SequentialGroup
    -0.68
     للمعارف
    -0.64
    AxisAlignment
    -0.64
    SourceChecksum
    -0.63
    IVEREF
    -0.62
     CURIAM
    -0.60
    POSITIVE LOGITS
    >{@
    0.59
     WW
    0.48
     World
    0.48
     Wij
    0.47
    WW
    0.46
     WO
    0.44
     FontWeight
    0.44
     Wor
    0.44
    CWE
    0.43
    %=
    0.43
    Activations Density 0.303%

    No Known Activations