© 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. 14546
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating a need for methods and systems to address specific problems

    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
     onCancelled
    -0.61
    xFFFFFF
    -0.58
    hésite
    -0.57
    efeller
    -0.52
    sizeCache
    -0.51
     cualquiera
    -0.51
     thorium
    -0.51
     vänt
    -0.50
     Thug
    -0.50
    ниципа
    -0.49
    POSITIVE LOGITS
    addContainerGap
    0.63
     suitable
    0.55
     reliable
    0.53
     escape
    0.51
    polator
    0.51
     capable
    0.50
     dependable
    0.50
     authoritative
    0.49
    queryInterface
    0.48
     aans
    0.48
    Activations Density 0.447%

    No Known Activations