© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8800
    Prev
    Next
    INDEX
    Explanations

    phrases that denote relationships or connections between different subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.11
     cherchés
    -0.87
     beginnetje
    -0.83
     Infórmanos
    -0.79
     snippetHide
    -0.79
     pinulongan
    -0.79
     Taktlose
    -0.78
    elemField
    -0.78
     disambiguazione
    -0.78
     Signalez
    -0.77
    POSITIVE LOGITS
    ↵
    0.73
    ↵↵
    0.65
     the
    0.63
    2
    0.62
     
    0.62
    <eos>
    0.59
    0
    0.58
    1
    0.57
     of
    0.55
     (
    0.52
    Activations Density 1.036%

    No Known Activations