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. 6792
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or resistance to various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Expressing disagreement or being "against" something

    np_acts-logits-general · gemini-2.0-flash

    opposition to or favor

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    nloa
    -0.45
     BBC
    -0.45
    ErrUnexpectedEOF
    -0.44
     crossorigin
    -0.44
    AccessorTable
    -0.44
     oracles
    -0.44
    utnik
    -0.44
     oracle
    -0.42
    rungsseite
    -0.42
     NRK
    -0.42
    POSITIVE LOGITS
     oppose
    0.90
     opposes
    0.85
     opposed
    0.81
    opposed
    0.74
    opposition
    0.71
     opposition
    0.69
     opposing
    0.65
     oppos
    0.61
    反对
    0.61
    反対
    0.61
    Activations Density 0.494%

    No Known Activations