© 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. 4454
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude and acknowledgment in correspondence

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

    formal closing phrases and courtesies in professional correspondence.

    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
    BASEPATH
    -0.53
    BeginContext
    -0.48
    LookAnd
    -0.47
    Witam
    -0.46
    tagHelperRunner
    -0.45
     ContentValues
    -0.44
     يتيمه
    -0.44
    contentLoaded
    -0.44
    pleaños
    -0.42
    IsContent
    -0.41
    POSITIVE LOGITS
    Regards
    1.42
    Sincerely
    1.41
     Regards
    1.39
     best
    1.37
    Best
    1.31
     Best
    1.30
     Sincerely
    1.30
    best
    1.23
    regards
    1.22
     regards
    1.21
    Activations Density 0.328%

    No Known Activations