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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 538
    Prev
    Next
    INDEX
    Explanations

    references to user privacy and data protection

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

    Precedes "they," a period, or company designation

    np_acts-logits-general · gemini-2.0-flash

    website or site

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fjspx
    -0.41
    gebob
    -0.40
     ?>>
    -0.38
     uğ
    -0.37
    RenderAtEndOf
    -0.37
     rodada
    -0.36
    ),),
    -0.36
     banget
    -0.35
    OCCURRED
    -0.35
     harder
    -0.34
    POSITIVE LOGITS
    ſelf
    0.49
     jspb
    0.48
    ſelves
    0.47
    期刊论文
    0.46
     assets
    0.45
    featureID
    0.45
     verbal
    0.45
    󰀄
    0.44
    twimg
    0.43
    adaptiveStyles
    0.42
    Activations Density 0.311%

    No Known Activations