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. 25-GEMMASCOPE-RES-16K
    6. 4742
    Prev
    Next
    INDEX
    Explanations

    statements and questions related to legal regulations around communication technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.63
     ddelweddau
    -0.59
    رشف
    -0.56
    šanai
    -0.52
    AndEndTag
    -0.51
     Normdatei
    -0.51
    WriteTagHelper
    -0.50
    ,:);
    -0.50
    iseite
    -0.50
    setAccessible
    -0.48
    POSITIVE LOGITS
     est
    1.20
    est
    0.79
     sera
    0.77
     sont
    0.77
     doit
    0.77
     était
    0.77
     serait
    0.73
     n
    0.72
     ne
    0.72
     existe
    0.70
    Activations Density 0.122%

    No Known Activations