Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 3897
    Prev
    Next
    INDEX
    Explanations

    the presence of specific attributes or conditions in a dataset

    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
    ficult
    -0.68
     vägen
    -0.68
    uable
    -0.66
    apeno
    -0.65
     utopian
    -0.64
    nytt
    -0.62
     fatica
    -0.62
     rehearing
    -0.62
     AWARDS
    -0.61
    MLLoader
    -0.60
    POSITIVE LOGITS
     presence
    1.68
    presence
    1.60
     Presence
    1.47
    Presence
    1.42
     présence
    1.20
     presencia
    1.15
     absence
    1.13
    absence
    1.11
    Absence
    1.07
     Absence
    1.01
    Activations Density 0.168%

    No Known Activations