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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3945
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical operation and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sadly
    -0.69
     gestionar
    -0.69
    Sadly
    -0.68
     behaviours
    -0.66
     للمعارف
    -0.64
     يتيمه
    -0.63
     sadly
    -0.62
     optimisation
    -0.60
    ustainable
    -0.60
     prioritise
    -0.59
    POSITIVE LOGITS
     louer
    0.59
     shall
    0.58
     objectionable
    0.58
     satisfactory
    0.57
     sauter
    0.56
     satisfactorily
    0.56
     rire
    0.55
     hereinafter
    0.54
     furnishes
    0.54
     fantaisie
    0.54
    Activations Density 1.811%

    No Known Activations