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. 8341
    Prev
    Next
    INDEX
    Explanations

    terms related to processes, systems, and operational dynamics in technical contexts

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

    Follows nouns

    np_acts-logits-general · gemini-2.0-flash

    verbs describing states or actions

    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
     gynhyrchwyd
    -0.73
     EconPapers
    -0.69
    sizeCache
    -0.61
    ագրություններ
    -0.59
     January
    -0.58
    RenderAtEndOf
    -0.57
    SBATCH
    -0.56
    ":
    
    -0.54
    ')):
    -0.54
     disambiguazione
    -0.54
    POSITIVE LOGITS
     invis
    0.67
    ~
    0.66
     derni
    0.58
     afterwards
    0.57
     after
    0.55
     everywhere
    0.54
     preuve
    0.53
     before
    0.53
     unconsciously
    0.53
     inexp
    0.53
    Activations Density 0.074%

    No Known Activations