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. 15-GEMMASCOPE-RES-16K
    6. 2316
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related structures within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blij
    -0.50
     ostensibly
    -0.49
    中に
    -0.46
    ווא
    -0.46
     zilver
    -0.44
    "?>
    -0.44
     actuels
    -0.43
     rarement
    -0.43
     veiligheid
    -0.43
     sonno
    -0.42
    POSITIVE LOGITS
    +#+#
    1.12
    EDEFAULT
    1.03
     propOrder
    0.97
     nakalista
    0.90
     pinulongan
    0.83
    SourceChecksum
    0.82
    GEBURTSDATUM
    0.82
    ⓧ
    0.81
    protoimpl
    0.80
     esternos
    0.79
    Activations Density 0.665%

    No Known Activations