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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9287
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their usage in constructing sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$@"
    -0.54
    KommentareTeilen
    -0.53
     vitae
    -0.49
    "),
    
    -0.47
    )':
    -0.46
    ]";
    -0.46
    '");
    -0.46
    cipit
    -0.45
    ówczas
    -0.44
    Hochspringen
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.83
    NameInMap
    0.80
     المعيارى
    0.77
    resave
    0.77
    Демографія
    0.74
     Monfieur
    0.72
     Argentino
    0.71
    Uninitialized
    0.71
    AddTagHelper
    0.70
    Aholisi
    0.69
    Activations Density 0.180%

    No Known Activations