Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 120787
    Prev
    Next
    INDEX
    Explanations

    references to softness or soft qualities

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

    softness and its descriptors

    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
     numerus
    -0.55
     eventName
    -0.54
     eventId
    -0.49
     dequeue
    -0.48
    AddTagHelper
    -0.48
    DataMember
    -0.47
     occurrences
    -0.46
    kwür
    -0.46
     mileage
    -0.45
     MyClass
    -0.45
    POSITIVE LOGITS
     soft
    2.16
     Soft
    2.08
    soft
    2.08
    Soft
    2.00
     SOFT
    1.87
    SOFT
    1.70
     softer
    1.38
     softness
    1.34
     softly
    1.32
     softens
    1.32
    Activations Density 0.004%

    No Known Activations