© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12226
    Prev
    Next
    INDEX
    Explanations

    references to opposition or resistance in various contexts

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

    "against"

    np_acts-logits-general · gemini-2.0-flash

    expressing opposition or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nivå
    -0.44
     informacija
    -0.43
     Administrativna
    -0.38
     AssemblyCulture
    -0.38
    adeloupe
    -0.38
    Tikang
    -0.37
    oarece
    -0.37
    erweise
    -0.36
    الدراسه
    -0.36
    ulemon
    -0.36
    POSITIVE LOGITS
     Against
    1.08
    Against
    1.06
     against
    1.06
    against
    1.05
     AGAINST
    0.93
     contre
    0.68
     gegen
    0.68
     backdrop
    0.63
     melawan
    0.60
     против
    0.60
    Activations Density 0.133%

    No Known Activations