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. 1-GEMMASCOPE-RES-16K
    6. 6220
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and configurations, particularly in a digital or computing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.01
     doInBackground
    -0.87
     Bessie
    -0.78
     EClass
    -0.75
     Pompey
    -0.73
    出版年
    -0.72
     CreateTagHelper
    -0.71
    yntaxException
    -0.71
     estekak
    -0.70
     Aphrodite
    -0.69
    POSITIVE LOGITS
    jal
    1.13
     Ral
    1.10
    JAL
    1.09
     Jol
    1.05
     thal
    0.99
     ral
    0.97
     NEL
    0.97
    ral
    0.97
    Jal
    0.97
     SIL
    0.96
    Activations Density 3.254%

    No Known Activations