© 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. 2-GEMMASCOPE-RES-16K
    6. 6009
    Prev
    Next
    INDEX
    Explanations

    words related to suitability or appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nur
    -0.53
    yl
    -0.52
    fahren
    -0.52
    র
    -0.50
     teng
    -0.49
    sol
    -0.49
    inner
    -0.48
    hen
    -0.48
    лено
    -0.48
    klo
    -0.48
    POSITIVE LOGITS
    Appropriate
    1.71
     Appropriate
    1.65
    appropriate
    1.62
     appropriate
    1.55
     APPROPRI
    1.30
    Inappropriate
    1.28
     appropriateness
    1.28
     inappropriate
    1.22
     apropiado
    1.21
     applicable
    1.10
    Activations Density 0.093%

    No Known Activations