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. 7-GEMMASCOPE-RES-16K
    6. 15658
    Prev
    Next
    INDEX
    Explanations

    references to the word "strip" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orianCalendar
    -0.53
     FileWriter
    -0.50
    LookAnd
    -0.49
     toJson
    -0.48
    ReusableCell
    -0.47
    tableFuture
    -0.46
    ClientSize
    -0.46
    outState
    -0.45
    bein
    -0.45
     FileNotFound
    -0.44
    POSITIVE LOGITS
     strip
    3.00
     Strip
    2.88
    strip
    2.72
    Strip
    2.69
     STRIP
    2.66
     strips
    2.58
     Strips
    2.47
     stripping
    2.44
     stripped
    2.25
    strips
    2.25
    Activations Density 0.194%

    No Known Activations