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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103093
    Prev
    Next
    INDEX
    Explanations

    resources and support related to mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     recoil
    -0.38
     يتيمه
    -0.37
    どうなる
    -0.36
    ampunk
    -0.36
    styleType
    -0.36
    Zag
    -0.35
    orkel
    -0.35
    quing
    -0.34
     Achtung
    -0.34
     top
    -0.34
    POSITIVE LOGITS
     myſelf
    0.62
     itſelf
    0.58
    ſelf
    0.57
    MessageTagHelper
    0.56
    aarrggbb
    0.54
     محفوظة
    0.54
     faſt
    0.54
    OGND
    0.54
    VIAF
    0.53
    存于互联网档案馆
    0.52
    Activations Density 0.014%

    No Known Activations