Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 378
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to horizontal and vertical orientations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offici
    -0.41
     noDo
    -0.40
    يميديا
    -0.40
    醐
    -0.37
    </tfoot>
    -0.37
    scribers
    -0.37
    NameInMap
    -0.36
    enumi
    -0.36
    المشاركات
    -0.36
    جوايز
    -0.35
    POSITIVE LOGITS
     horizontal
    2.30
     Horizontal
    2.14
    horizontal
    2.05
    Horizontal
    2.02
     horizontally
    1.94
     horizont
    1.73
     orizz
    1.70
    HORIZONTAL
    1.66
     horiz
    1.62
     горизонта
    1.55
    Activations Density 0.264%

    No Known Activations