© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9945
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presence" and its variations, indicating a focus on the concept of being present or absent in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Explora
    -0.51
     Kamil
    -0.48
    +#+#
    -0.47
    matism
    -0.47
     glutamate
    -0.47
    cuma
    -0.47
     dikes
    -0.46
     alimen
    -0.45
     alimentare
    -0.43
     phosp
    -0.43
    POSITIVE LOGITS
     presence
    1.87
    presence
    1.78
     Presence
    1.77
    Presence
    1.73
     présence
    1.67
     присут
    1.48
     presenza
    1.46
     presencia
    1.41
     presença
    1.40
     aanwezig
    1.39
    Activations Density 0.365%

    No Known Activations