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. 19-GEMMASCOPE-RES-16K
    6. 176
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery or systems involved in drilling operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.91
    BeginInit
    -0.88
    AndEndTag
    -0.85
     Signalez
    -0.80
     متعلقه
    -0.80
    StreetMap
    -0.77
     fountains
    -0.75
     nakalista
    -0.75
     rooftops
    -0.75
     ModelExpression
    -0.75
    POSITIVE LOGITS
     position
    0.60
     zitten
    0.55
     inside
    0.54
     longitud
    0.53
     altezza
    0.53
     positioned
    0.52
     underneath
    0.51
     Position
    0.51
     recessed
    0.49
     thickness
    0.49
    Activations Density 1.183%

    No Known Activations