© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 99924
    Prev
    Next
    INDEX
    Explanations

    elements related to AJAX requests and their configurations

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

    accessing user input

    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
     betweenstory
    -0.59
    期刊论文
    -0.51
     onBind
    -0.48
    ########.
    -0.47
    حياته
    -0.47
    पया
    -0.46
    +#+
    -0.45
    EndProject
    -0.44
    /**
    -0.44
    IntoConstraints
    -0.43
    POSITIVE LOGITS
     comuniques
    0.47
     Kugel
    0.43
    XmlAccessType
    0.43
     send
    0.40
    Via
    0.39
    aarrggbb
    0.38
    WriteTagHelper
    0.37
     accomplished
    0.37
     implicitly
    0.36
    AutoScaleMode
    0.36
    Activations Density 0.089%

    No Known Activations