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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8415
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical devices and circuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.59
     surla
    -0.58
     مشين
    -0.57
    AutoScaleMode
    -0.56
    quate
    -0.52
    PerformLayout
    -0.52
    textra
    -0.51
     חיצוניים
    -0.49
    ValueStyle
    -0.49
     spina
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.43
     banking
    0.35
     AC
    0.34
    ACCEPTED
    0.34
     teknis
    0.34
     ویکی‌پدی
    0.34
     esistono
    0.34
    :✨
    0.33
     transférez
    0.31
     téc
    0.30
    Activations Density 0.457%

    No Known Activations