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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7115
    Prev
    Next
    INDEX
    Explanations

    terms related to automation and automatic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.56
     vacas
    -0.48
    alternate
    -0.46
     veterans
    -0.45
     szcz
    -0.44
    extré
    -0.43
     village
    -0.43
     veteran
    -0.43
     Village
    -0.42
     pizarra
    -0.42
    POSITIVE LOGITS
    Never
    0.75
     Never
    0.74
    never
    0.63
     never
    0.62
    Билгалдахарш
    0.61
    NEVER
    0.61
     auto
    0.60
    Always
    0.59
    findpost
    0.57
     Always
    0.57
    Activations Density 0.256%

    No Known Activations