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. 2-GEMMASCOPE-RES-16K
    6. 3664
    Prev
    Next
    INDEX
    Explanations

    references to data types in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.96
     ſeveral
    -0.94
    RegistryLite
    -0.91
    IonicModule
    -0.90
     doubtnut
    -0.86
     ſever
    -0.85
     Theſe
    -0.85
     Anſ
    -0.84
    ,:);
    -0.83
     raiſ
    -0.83
    POSITIVE LOGITS
     type
    3.54
    type
    3.00
     Type
    3.00
     TYPE
    2.84
     types
    2.78
    Type
    2.71
     tipo
    2.55
    TYPE
    2.50
    types
    2.25
     Types
    2.22
    Activations Density 0.152%

    No Known Activations