© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99945
    Prev
    Next
    INDEX
    Explanations

    the word "totally" used in various contexts to emphasize strong approval or agreement

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

    "totally" followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Voci
    -0.49
     Lese
    -0.47
    clerview
    -0.43
    ähr
    -0.42
    Ivoire
    -0.41
    Derp
    -0.41
     ricev
    -0.41
     Ads
    -0.41
     HasFactory
    -0.40
    äiv
    -0.40
    POSITIVE LOGITS
     totally
    1.93
    totally
    1.88
    Totally
    1.75
     Totally
    1.72
     completely
    1.38
     totalmente
    1.36
    completely
    1.27
     Completely
    1.26
    Completely
    1.24
     totalement
    1.21
    Activations Density 0.003%

    No Known Activations