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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6778
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to mechanical and material processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    shaped objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numberOfRows
    -0.43
    aarrggbb
    -0.43
     mejorado
    -0.38
     obligado
    -0.36
     genaue
    -0.35
     estaremos
    -0.35
     begge
    -0.33
     sayang
    -0.32
     vær
    -0.32
     hendes
    -0.31
    POSITIVE LOGITS
    CloseOperation
    0.85
    DockStyle
    0.77
     BoxFit
    0.69
    ſelf
    0.66
     pleaſure
    0.63
     faſt
    0.59
    ſelves
    0.58
     utafitiHapana
    0.58
     ſche
    0.57
     GenerationType
    0.57
    Activations Density 9.126%

    No Known Activations