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. 21-GEMMASCOPE-RES-16K
    6. 2081
    Prev
    Next
    INDEX
    Explanations

    terms related to biology, specifically focusing on mollusks and related species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nationality
    -0.60
     EconPapers
    -0.59
    "}}>
    -0.56
     vaut
    -0.55
     betweenstory
    -0.55
    ]<<
    -0.55
     measles
    -0.54
     Dario
    -0.54
    rimiento
    -0.54
     Adamson
    -0.54
    POSITIVE LOGITS
     shell
    1.69
     Shell
    1.59
     shells
    1.58
    Shell
    1.55
    shell
    1.48
     Shells
    1.43
     SHELL
    1.41
    shells
    1.26
    SHELL
    1.23
     shelled
    1.10
    Activations Density 0.161%

    No Known Activations