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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4218
    Prev
    Next
    INDEX
    Explanations

    terms related to actions and activities, especially those in a transactional or operational context

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

    Verbs ending in "ing"

    np_acts-logits-general · gemini-2.0-flash

    activities ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inghouse
    -0.82
    +#+
    -0.77
     VIAF
    -0.74
    breeding
    -0.72
    Funding
    -0.72
     funding
    -0.71
    Filing
    -0.70
    InstanceState
    -0.70
    funding
    -0.69
    nadequate
    -0.69
    POSITIVE LOGITS
    tons
    0.79
    redients
    0.78
    redient
    0.77
     spree
    0.73
    gggg
    0.73
    ggg
    0.63
    ton
    0.63
     techniques
    0.61
    ly
    0.60
     spre
    0.60
    Activations Density 0.660%

    No Known Activations