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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 9820
    Prev
    Next
    INDEX
    Explanations

    expressions of personal thoughts and feelings, particularly those related to motherhood and personal struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.65
     MainAxisSize
    -0.65
     ddelweddau
    -0.65
    aarrggbb
    -0.62
     EconPapers
    -0.61
    期刊论文
    -0.59
    ביוגרפיה
    -0.58
    nezeu
    -0.57
    MockBean
    -0.55
     raiſ
    -0.55
    POSITIVE LOGITS
     honestly
    0.48
     genuinely
    0.44
    AndEndTag
    0.41
     admittedly
    0.40
     mainly
    0.39
     wanna
    0.37
     definitely
    0.36
     totally
    0.36
     personally
    0.35
     Army
    0.34
    Activations Density 0.323%

    No Known Activations