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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12914
    Prev
    Next
    INDEX
    Explanations

    biomedical terms related to gene expression and molecular biology

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

    after or including "Error" or "Round"

    np_acts-logits-general · gemini-2.0-flash

    Round, Inhibition, Error, Step, Pixel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.44
     виправивши
    -1.42
    ^(@)
    -1.28
    AutoScaleMode
    -1.26
    +#+#
    -1.21
    脚注の使い方
    -1.18
    }%
    
    -1.15
     oprot
    -1.14
    تقاوى
    -1.13
     MonoBehaviour
    -1.11
    POSITIVE LOGITS
     is
    0.56
    :
    0.52
     de
    0.51
     M
    0.51
     di
    0.50
     T
    0.49
     e
    0.49
     
    0.48
     I
    0.48
     d
    0.48
    Activations Density 0.413%

    No Known Activations