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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3144
    Prev
    Next
    INDEX
    Explanations

    issues related to critiques or concerns in writing

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

    slightness or moderation

    np_acts-logits-general · gemini-2.0-flash

    relative degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.81
    WebServlet
    -0.75
    不但
    -0.59
    oltre
    -0.54
    ędzie
    -0.52
    ModelMap
    -0.52
    +#+#
    -0.50
    isSuccessful
    -0.50
    脚注の使い方
    -0.49
    enumi
    -0.49
    POSITIVE LOGITS
     slightly
    1.17
     Slightly
    1.05
    slightly
    1.00
     somewhat
    0.98
     hơi
    0.93
    Slightly
    0.92
     slight
    0.91
    もう少し
    0.91
     немного
    0.91
     trochu
    0.88
    Activations Density 0.342%

    No Known Activations