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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7096
    Prev
    Next
    INDEX
    Explanations

    terms related to delicacy or gentleness in various contexts

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

    associated with fragility or gentleness

    np_acts-logits-general · gemini-2.0-flash

    delicate or gentle quality

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CreateTagHelper
    -0.51
     Wikimedijinoj
    -0.45
    zbęd
    -0.43
    twimg
    -0.43
    สน
    -0.42
     grecque
    -0.41
     wireType
    -0.40
     citoy
    -0.40
    Πηγές
    -0.40
    autonomie
    -0.39
    POSITIVE LOGITS
     delicate
    1.41
     gentle
    1.29
     delicately
    1.20
     gently
    1.14
     Gentle
    1.13
    Gentle
    1.13
    gentle
    1.10
     Gently
    1.09
     delikat
    1.08
     delicado
    1.05
    Activations Density 0.254%

    No Known Activations