© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    informal language and personal pronouns related to expressions of self and interpersonal communication

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

    informal internet slang and colloquial contractions (like "u" for "you", "wat" for "what", "ur" for "your").

    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
     Infórmanos
    -0.48
    >();
    -0.46
    >>();
    -0.45
    estacks
    -0.45
    ��������
    -0.44
    ";
    -0.42
    ://
    -0.41
     Jahrhunderts
    -0.40
    ď
    -0.40
     PeEnEo
    -0.40
    POSITIVE LOGITS
    Спасылкі
    0.59
    Referanser
    0.58
    selben
    0.56
     الحره
    0.52
    קישורים
    0.51
    Referencie
    0.50
    сылкі
    0.49
    Зноскі
    0.49
    quele
    0.49
    まま
    0.48
    Activations Density 0.612%

    No Known Activations