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. 5-GEMMASCOPE-RES-16K
    6. 13543
    Prev
    Next
    INDEX
    Explanations

    Java code related to integer data types, specifically involving parsing and processing integer values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.67
    mogat
    -0.66
     ComVisible
    -0.65
     	e
    -0.63
     bVar
    -0.63
     maș
    -0.60
    guenos
    -0.60
    ēc
    -0.60
    chaun
    -0.60
     seguente
    -0.59
    POSITIVE LOGITS
     integer
    1.74
    integer
    1.66
     integers
    1.62
     Integer
    1.58
    Integer
    1.55
    getInteger
    1.48
    INTEGER
    1.38
    integers
    1.28
     INTEGER
    1.26
     Inte
    0.95
    Activations Density 0.033%

    No Known Activations