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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56826
    Prev
    Next
    INDEX
    Explanations

    references to achievements and accomplishments

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

    discussing achievements

    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
     Sandler
    -0.40
    ądz
    -0.39
     rail
    -0.39
    <h4>
    -0.38
     mosque
    -0.37
     old
    -0.37
    Initially
    -0.36
    orghini
    -0.36
    Lips
    -0.36
    蚪
    -0.36
    POSITIVE LOGITS
     achievements
    1.27
     Achievement
    1.25
     achievement
    1.23
    Achievement
    1.22
     Achievements
    1.18
    achievement
    1.13
     accomplishment
    1.08
     accomplishments
    1.05
    complishments
    1.03
    Achievements
    1.00
    Activations Density 0.007%

    No Known Activations