© 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. 12-GEMMASCOPE-RES-16K
    6. 10706
    Prev
    Next
    INDEX
    Explanations

    phrases related to executing processes and methodologies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impea
    -0.58
     maroca
    -0.58
    mable
    -0.57
    konomi
    -0.57
    Geplaatst
    -0.57
     madden
    -0.56
     ingrat
    -0.56
     comprando
    -0.55
     spirituale
    -0.54
    ToRemove
    -0.54
    POSITIVE LOGITS
    conducted
    0.87
     conducted
    0.85
    การ
    0.85
     extensive
    0.81
     successful
    0.78
    successful
    0.76
    performed
    0.76
    Extensive
    0.75
     Extensive
    0.74
    多次
    0.74
    Activations Density 0.945%

    No Known Activations