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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8892
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical estimation and modeling, particularly in the context of advanced statistical methods and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    الحياه
    -0.53
     Quels
    -0.47
     anzunehmen
    -0.46
    RTLD
    -0.45
    مراجع
    -0.44
     whatever
    -0.43
    setArguments
    -0.43
     AutoMapper
    -0.43
     pensieri
    -0.43
     enfans
    -0.43
    POSITIVE LOGITS
    djangoproject
    0.77
     GenerationType
    0.74
    virons
    0.65
    Filmographie
    0.64
    dataProvider
    0.61
     CWE
    0.61
    市镇
    0.60
    IntoConstraints
    0.59
    ondissement
    0.58
    ReusableCell
    0.58
    Activations Density 0.774%

    No Known Activations