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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5960
    Prev
    Next
    INDEX
    Explanations

    terms related to educational programs and models that aim to improve practices and promote innovative strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.75
    EndContext
    -0.74
    makeText
    -0.74
    MigrationBuilder
    -0.73
    principalTable
    -0.72
    ISupport
    -0.62
    IntoConstraints
    -0.59
     resourceCulture
    -0.56
    下载附件
    -0.55
     menim
    -0.55
    POSITIVE LOGITS
     ideas
    0.96
     innovations
    0.93
     innov
    0.92
     innovative
    0.84
     concepts
    0.81
     idea
    0.79
     innovate
    0.78
     innovation
    0.75
    innov
    0.75
     concept
    0.75
    Activations Density 0.760%

    No Known Activations