© 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. 18-GEMMASCOPE-RES-16K
    6. 8841
    Prev
    Next
    INDEX
    Explanations

    references to animals and their interactions in nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Types of animals

    np_acts-logits-general · gemini-2.0-flash

    animals and their physical characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.80
    +#+
    -0.62
    Geplaatst
    -0.61
    GraphicsUnit
    -0.59
     متعلقه
    -0.58
    IsContent
    -0.55
    clable
    -0.52
     Baillargeon
    -0.51
     gynhyrchwyd
    -0.51
     personalización
    -0.50
    POSITIVE LOGITS
     species
    0.62
     specie
    0.56
     breed
    0.55
     sauvages
    0.53
    whom
    0.53
    MockMvc
    0.53
     inhabiting
    0.52
     OFDb
    0.52
    们的
    0.51
     Species
    0.51
    Activations Density 0.619%

    No Known Activations