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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9250
    Prev
    Next
    INDEX
    Explanations

    elements related to dimensions and positions in a layout or graphical interface

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

    directional spatial properties and layout positioning terms (like left, right, top, bottom, padding, height, width).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MenuView
    -0.66
    Tembelea
    -0.59
     insular
    -0.56
     monog
    -0.56
     Anatom
    -0.55
    XmlAccessType
    -0.54
     ox
    -0.53
    󠁴
    -0.52
     auri
    -0.52
     noDo
    -0.52
    POSITIVE LOGITS
     duradero
    0.53
     pelatih
    0.47
     nación
    0.47
     Administrativna
    0.47
     keduanya
    0.47
     selben
    0.46
     térmico
    0.45
     Nachbarn
    0.43
     cárcel
    0.43
     cheminée
    0.42
    Activations Density 2.045%

    No Known Activations