© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7051
    Prev
    Next
    INDEX
    Explanations

    sequences related to terminal regions and flanking sequences in genetic material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.64
    Hentet
    -0.59
    abestanden
    -0.59
    EndInit
    -0.58
     مناف
    -0.57
    consulté
    -0.55
     lccn
    -0.54
     odkazy
    -0.54
    Izvori
    -0.53
    windowFixed
    -0.53
    POSITIVE LOGITS
    AndEndTag
    0.62
    libft
    0.56
    prepend
    0.55
    ########.
    0.54
     Namur
    0.52
     }?>
    0.52
    ConverterFactory
    0.52
     precede
    0.51
    nestjs
    0.51
     immédi
    0.51
    Activations Density 0.632%

    No Known Activations