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. 15133
    Prev
    Next
    INDEX
    Explanations

    phrases related to the realization of goals and achievements

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

    Realizing or achievement of goals

    np_acts-logits-general · gemini-2.0-flash

    achieving goals

    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
     extranjera
    -0.47
    CppMethod
    -0.46
     amarilla
    -0.42
    новништво
    -0.40
    propTypes
    -0.40
    ništ
    -0.40
    essages
    -0.39
     Öffentlichkeit
    -0.39
     razonable
    -0.39
     sabbia
    -0.39
    POSITIVE LOGITS
     fulfillment
    0.81
     fulfill
    0.78
     fulfilment
    0.77
     fulfil
    0.74
    complish
    0.70
     accomplish
    0.69
     accomplishment
    0.69
     accomplishing
    0.67
     fulfilling
    0.67
     achievement
    0.66
    Activations Density 0.285%

    No Known Activations