Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3677
    Prev
    Next
    INDEX
    Explanations

    instances of the word "construction" and its variants, indicating a focus on discussions about construction processes or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.57
    berapa
    -0.57
     חיצוניים
    -0.55
    ➽
    -0.53
    interopRequire
    -0.50
     oczy
    -0.50
    getParameters
    -0.49
     paging
    -0.48
     Aufenthalts
    -0.48
    횟
    -0.48
    POSITIVE LOGITS
     construction
    1.92
     Construction
    1.74
    construction
    1.72
     construct
    1.72
    Construction
    1.71
    construct
    1.63
     Construct
    1.59
     CONSTRUCTION
    1.56
     constructed
    1.56
    Construct
    1.54
    Activations Density 0.099%

    No Known Activations