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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational structure and roles within companies

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

    Preceding words ending in "ed" or commas

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useRouter
    -0.70
     meille
    -0.68
     stedet
    -0.66
     useParams
    -0.65
     trasparente
    -0.65
     Giappone
    -0.64
     mukana
    -0.64
    zitter
    -0.64
     feveral
    -0.62
     quelcon
    -0.61
    POSITIVE LOGITS
    buttonBar
    0.65
    memoized
    0.64
     himo
    0.59
    }\]
    0.53
    RegressionTest
    0.52
    ++)
    
    0.52
    IContainer
    0.51
     pinulongan
    0.50
    ]>=
    0.50
    __':
    0.49
    Activations Density 0.594%

    No Known Activations