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. 3182
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or locations associated with the word "El."

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

    proper nouns and place names, particularly "El" followed by a second word that forms a geographic or institutional name.

    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
    __*/
    -0.45
     prácticas
    -0.44
     herida
    -0.44
     totalidad
    -0.43
     poussière
    -0.43
     cálido
    -0.43
     costumbres
    -0.42
     detailsNormal
    -0.42
     conseguenze
    -0.42
     normalidad
    -0.42
    POSITIVE LOGITS
     EL
    0.67
     el
    0.67
     El
    0.64
     Elgin
    0.62
     elm
    0.58
     Ell
    0.57
     elb
    0.56
     ell
    0.54
     Eld
    0.54
     ellip
    0.54
    Activations Density 0.115%

    No Known Activations