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. 18-GEMMASCOPE-RES-16K
    6. 1183
    Prev
    Next
    INDEX
    Explanations

    references to "pool" or "pooling" in various contexts

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

    "pool" or related terms

    np_acts-logits-general · gemini-2.0-flash

    pool of X or pool layers

    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
    IUrlHelper
    -0.84
     متعلقه
    -0.72
    IBOutlet
    -0.63
     linkovi
    -0.63
    hyrchwyd
    -0.62
    Hentet
    -0.62
     TestCase
    -0.60
    contentLoaded
    -0.59
    neté
    -0.58
     Nicholls
    -0.58
    POSITIVE LOGITS
     pool
    1.25
     Pool
    1.22
     pools
    1.22
     POOL
    1.17
    pools
    1.12
     Pools
    1.11
    pool
    1.09
    Pool
    1.04
    Pools
    1.02
    POOL
    0.98
    Activations Density 0.128%

    No Known Activations