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. 8280
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology and citations related to cases

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

    ending in "ing"

    np_acts-logits-general · gemini-2.0-flash

    -ing / -ing's

    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
     McCabe
    -0.60
     Parrish
    -0.55
     Wilcox
    -0.49
     Alvarez
    -0.49
     Quân
    -0.48
     evac
    -0.47
     McClellan
    -0.47
     McGee
    -0.45
     gradova
    -0.45
    omni
    -0.45
    POSITIVE LOGITS
    ining
    1.15
    ding
    1.13
    inting
    1.11
    ZING
    1.10
    DING
    1.08
    ising
    1.08
    eling
    1.07
    TING
    1.07
    ning
    1.07
    fting
    1.06
    Activations Density 0.380%

    No Known Activations