© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2642
    Prev
    Next
    INDEX
    Explanations

    repeated punctuation or dividers within the text

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

    ellipsis marks and structural separators in text formatting.

    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
    transQ
    -0.67
    expandindo
    -0.63
    PreferredItem
    -0.63
    MessageTagHelper
    -0.61
     ब्रेकडाउन
    -0.60
    webElementXpaths
    -0.60
     المعيارى
    -0.60
    期刊论文
    -0.59
    smithy
    -0.57
     تكبرها
    -0.55
    POSITIVE LOGITS
    wapV
    0.37
    #+#
    0.34
     isolé
    0.34
    tagHelperRunner
    0.33
     bowiem
    0.31
     suiv
    0.30
     
    0.30
     chodzi
    0.29
     séjour
    0.28
     segni
    0.28
    Activations Density 0.068%

    No Known Activations