Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5864
    Prev
    Next
    INDEX
    Explanations

    references to wildlife-related governance and incidents

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

    Safari or wildlife-related contexts

    np_acts-logits-general · gemini-2.0-flash

    safari and wildlife

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.49
    abuhan
    -0.44
    oa̍t
    -0.42
    capulco
    -0.42
     moulin
    -0.42
     gudang
    -0.41
     siglos
    -0.41
    chism
    -0.40
     Skate
    -0.40
     Harrell
    -0.39
    POSITIVE LOGITS
     safari
    0.85
     Kruger
    0.81
     Tanzania
    0.72
     saf
    0.72
     conservation
    0.71
    LookAnd
    0.71
     lodges
    0.71
     elephants
    0.71
     createState
    0.70
     Safari
    0.69
    Activations Density 0.085%

    No Known Activations