© 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. 8-GEMMASCOPE-RES-16K
    11. 4376
    Prev
    Next
    INDEX
    Explanations

    discussions about the nature and classification of disabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwitchCompat
    -0.55
     carefully
    -0.49
     ryb
    -0.47
    innis
    -0.47
    ofire
    -0.46
     ribos
    -0.45
     prison
    -0.45
     PyLong
    -0.45
     juries
    -0.45
     AsyncTask
    -0.45
    POSITIVE LOGITS
    存于互联网档案馆
    0.85
     kasarigan
    0.71
     distanciation
    0.69
    -------------</
    0.68
    tagHelperRunner
    0.64
    ftagPool
    0.63
    istoitu
    0.63
    RectangleBorder
    0.63
     CreateTagHelper
    0.62
    addPreferredGap
    0.62
    Activations Density 0.671%

    No Known Activations