© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to electronics and technology

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

    commas and punctuation in sentences, particularly in complex or academic text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    phrases and clauses that provide explanatory or descriptive details about a preceding noun or concept.

    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
     Herrn
    -0.57
     Mr
    -0.55
    Mr
    -0.51
     آقای
    -0.45
    modelBuilder
    -0.44
    的他
    -0.43
    자인
    -0.42
     Kläger
    -0.41
    Vidite
    -0.41
     Mrs
    -0.41
    POSITIVE LOGITS
    RectangleBorder
    0.60
    AntiForgeryToken
    0.59
    MessageTagHelper
    0.59
    IndentedString
    0.55
    RTCF
    0.55
     protoimpl
    0.55
    uxxxx
    0.52
    parsedMessage
    0.52
    AutoScaleMode
    0.52
     CreateTagHelper
    0.50
    Activations Density 3.188%

    No Known Activations