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. 1-GEMMASCOPE-RES-16K
    6. 2751
    Prev
    Next
    INDEX
    Explanations

    instances of the word "worry" along with contexts indicating managerial or administrative concerns

    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
    SequentialGroup
    -0.58
     foul
    -0.44
     bed
    -0.42
    JpaRepository
    -0.41
     Foul
    -0.41
     river
    -0.40
     rope
    -0.39
    ModelBuilder
    -0.39
     JpaRepository
    -0.39
     challenged
    -0.39
    POSITIVE LOGITS
     AssemblyCulture
    0.72
     kasarigan
    0.71
    admin
    0.68
     queſta
    0.60
    Stories
    0.59
    auth
    0.59
     Offisielt
    0.58
     Worlds
    0.56
     Wikimedijinoj
    0.54
    STORY
    0.54
    Activations Density 0.270%

    No Known Activations