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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 949
    Prev
    Next
    INDEX
    Explanations

    many different things, primarily locations, particularly countries and states, but secondarily also something related to the 6 million dollar man

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     licorne
    -0.60
     prestazioni
    -0.60
     NgModule
    -0.56
     fatica
    -0.54
    klart
    -0.53
     legais
    -0.52
    ernalia
    -0.51
    osoba
    -0.51
     urdu
    -0.50
    resz
    -0.50
    POSITIVE LOGITS
    jds
    0.57
     препратки
    0.56
    detectChanges
    0.54
    ]")]
    0.49
     Thra
    0.49
     Cour
    0.48
     Normdatei
    0.48
     riser
    0.48
     costar
    0.48
    MemoryWarning
    0.47
    Activations Density 0.398%

    No Known Activations