© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 13699
    Prev
    Next
    INDEX
    Explanations

    syntax or formatting issues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.88
    WriteBarrier
    -0.87
    CodedInputStream
    -0.86
     getItemCount
    -0.80
    __*/
    -0.79
     AppCompatTheme
    -0.79
    Personensuche
    -0.78
     &___
    -0.78
    RenderAtEndOf
    -0.75
     EconPapers
    -0.74
    POSITIVE LOGITS
    <bos>
    0.63
    ‍♂️
    0.47
    ‍♀️
    0.46
    ,
    0.45
     useParams
    0.44
    recyclerview
    0.42
    lė
    0.40
    Compartir
    0.40
    viewpager
    0.40
    nī
    0.39
    Activations Density 0.055%

    No Known Activations