© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13591
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and social constructs of impact and efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.55
     A
    -0.51
    Autoritní
    -0.51
     what
    -0.50
    valently
    -0.49
    もっと
    -0.48
     something
    -0.48
     menos
    -0.48
     همان
    -0.47
    @
    -0.46
    POSITIVE LOGITS
     esternos
    0.81
     resourceCulture
    0.79
     inability
    0.69
     impossibility
    0.63
     insistence
    0.63
     $_"
    0.62
     §.
    0.61
     fragility
    0.60
     بالای
    0.60
     inadequacy
    0.60
    Activations Density 0.891%

    No Known Activations