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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15151
    Prev
    Next
    INDEX
    Explanations

    names of authors and researchers in scientific contexts

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

    Last names

    np_acts-logits-general · gemini-2.0-flash

    names in author lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.66
    expandindo
    -0.66
    adaptiveStyles
    -0.64
    Personensuche
    -0.63
     CreateTagHelper
    -0.62
     ब्रेकडाउन
    -0.62
     autorytatywna
    -0.60
     MessageBoxIcon
    -0.56
    Портали
    -0.56
    Derbyniad
    -0.56
    POSITIVE LOGITS
     Smith
    0.41
     MonoBehaviour
    0.39
     Kardashian
    0.38
    layoutParams
    0.37
     Chemist
    0.37
    chiha
    0.36
     chemist
    0.36
     bodas
    0.35
     ordinaire
    0.35
     anonyme
    0.35
    Activations Density 0.348%

    No Known Activations