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. 5-GEMMASCOPE-RES-16K
    6. 8646
    Prev
    Next
    INDEX
    Explanations

    references to challenges, limitations, and strategies in various contexts

    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
     navires
    -0.60
    uxxxx
    -0.56
     jambes
    -0.56
     prisonniers
    -0.55
     âmes
    -0.53
    SOUNDBITE
    -0.53
    angnya
    -0.52
     médicaments
    -0.51
     réfugiés
    -0.51
    ahnya
    -0.51
    POSITIVE LOGITS
     difficulties
    1.01
     challenges
    0.97
     insights
    0.94
     possibilities
    0.92
     differences
    0.92
     aspects
    0.92
     abilities
    0.91
    irements
    0.89
     considerations
    0.88
     choices
    0.87
    Activations Density 0.716%

    No Known Activations