© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 11814
    Prev
    Next
    INDEX
    Explanations

    instructions related to JSON encoding and handling special characters

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

    special characters and escape sequences that need to be escaped or encoded in strings.

    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
    ########.
    -0.52
     indisponible
    -0.49
     resourceCulture
    -0.48
     raffredd
    -0.42
     CreateTagHelper
    -0.42
    atorship
    -0.40
    躇
    -0.39
    Попис
    -0.39
     yük
    -0.38
     geomé
    -0.38
    POSITIVE LOGITS
     escaping
    0.91
     escape
    0.91
     escaped
    0.89
     escapes
    0.84
    escape
    0.76
     Escape
    0.74
    Escape
    0.71
     escap
    0.70
    escaped
    0.69
     unes
    0.63
    Activations Density 0.788%

    No Known Activations