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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30837
    Prev
    Next
    INDEX
    Explanations

    expressions related to achieving goals or completing tasks

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

    accomplish

    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
     indé
    -0.47
    Katso
    -0.47
     Negra
    -0.44
    gypti
    -0.42
    getById
    -0.41
     preghi
    -0.41
     ​​
    -0.40
    ärzt
    -0.40
    earcher
    -0.40
     leaflets
    -0.40
    POSITIVE LOGITS
    complish
    1.16
    complishments
    1.09
    complished
    1.02
     accomplish
    1.01
     accomplishment
    1.00
     accomplished
    0.94
     accomplishing
    0.94
     accomplishments
    0.93
    Accomplished
    0.78
     accomp
    0.72
    Activations Density 0.004%

    No Known Activations