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. 20-GEMMASCOPE-RES-131K
    6. 5465
    Prev
    Next
    INDEX
    Explanations

    phrases related to product superiority and people's perceptions of value

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

    absence, keep, objective, matter, like, again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.41
     تضيفلها
    -0.38
    BeginContext
    -0.38
    ◀
    -0.37
    Soorten
    -0.35
    Predecesor
    -0.35
     CAT
    -0.35
    CodedInputStream
    -0.35
     Intern
    -0.35
     برانيه
    -0.35
    POSITIVE LOGITS
     ioutil
    0.47
    piej
    0.47
     defStyleAttr
    0.46
    RectangleBorder
    0.44
    Хьажоргаш
    0.44
     doInBackground
    0.44
    帖最后由
    0.44
     becauſe
    0.44
     bancaria
    0.43
     morreu
    0.42
    Activations Density 0.073%

    No Known Activations