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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1330
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their achievements or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bend
    -0.65
     OFDb
    -0.64
     bend
    -0.63
    à
    -0.60
    bam
    -0.59
     inconvénients
    -0.59
    bend
    -0.58
     Travis
    -0.57
     Schie
    -0.57
    Defs
    -0.56
    POSITIVE LOGITS
    存于互联网档案馆
    0.90
    脚注の使い方
    0.88
     lilac
    0.88
     Lilac
    0.87
    InvalidProtocol
    0.87
     myſelf
    0.84
    Personensuche
    0.83
    SharedCtor
    0.82
     MainAxisSize
    0.81
    ViewFeatures
    0.81
    Activations Density 8.777%

    No Known Activations