© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5591
    Prev
    Next
    INDEX
    Explanations

    mentions of integers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.70
     chapter
    -0.64
     Obrador
    -0.56
    OGND
    -0.56
     chapters
    -0.56
    chapter
    -0.55
     Chapter
    -0.55
    +#+#
    -0.51
    Portály
    -0.49
    utnik
    -0.49
    POSITIVE LOGITS
     integer
    1.05
    integer
    0.88
     integers
    0.73
     evening
    0.69
     Integer
    0.68
    Integer
    0.66
     tonight
    0.65
    evening
    0.65
     Evening
    0.65
     evenings
    0.64
    Activations Density 0.036%

    No Known Activations