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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1317
    Prev
    Next
    INDEX
    Explanations

    terms related to data fields and instances in a structured format, particularly in a programming or data processing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arangay
    -0.67
    <bos>
    -0.65
    OGND
    -0.61
     laſſen
    -0.58
     BoxDecoration
    -0.58
     kaarangay
    -0.57
     avoient
    -0.57
    ientras
    -0.57
    StoryboardSegue
    -0.57
    vorschaubild
    -0.56
    POSITIVE LOGITS
    忑
    0.47
    日閲覧
    0.45
    بالإنجليزية
    0.40
    TokenName
    0.40
    Спољашње
    0.40
    Это
    0.38
    Его
    0.37
    最快更新
    0.37
     FTP
    0.35
    凝土
    0.35
    Activations Density 0.058%

    No Known Activations