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

    Neuronpedia

    APICircuit 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. 5785
    Prev
    Next
    INDEX
    Explanations

    URLs and links, especially those related to technical documentation and coding resources

    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
     resourceCulture
    -0.73
    omock
    -0.60
     Meksiku
    -0.59
     propOrder
    -0.56
     للمعارف
    -0.55
     AssemblyTitle
    -0.54
     متعلقه
    -0.54
    tanleria
    -0.53
    fjspx
    -0.52
    ---*/
    -0.52
    POSITIVE LOGITS
    #:
    1.02
    #
    1.01
    #/
    1.00
    #.
    0.96
    #!/
    0.87
    #!
    0.84
    \#
    0.79
    ?&
    0.76
    ?_
    0.72
    #-
    0.71
    Activations Density 0.743%

    No Known Activations