© 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. 11578
    Prev
    Next
    INDEX
    Explanations

    personal reflections and expressions of emotional experience

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

    first-person singular pronouns and related contractions expressing personal perspective or subjective experience.

    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
     MainAxisSize
    -0.63
     raiſ
    -0.62
    期刊论文
    -0.55
    DockStyle
    -0.55
    ificantly
    -0.52
    MockBean
    -0.51
    ſelf
    -0.50
    LookAnd
    -0.49
     ſeveral
    -0.49
     diſt
    -0.48
    POSITIVE LOGITS
     continuously
    0.45
     honestly
    0.42
     initially
    0.42
     principalmente
    0.41
     mainly
    0.40
     inherently
    0.40
     personally
    0.40
    AndEndTag
    0.39
     automatically
    0.39
     definitely
    0.39
    Activations Density 0.320%

    No Known Activations