© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2618
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software configuration and management

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

    Software or component installation/setup

    np_acts-logits-general · gemini-2.0-flash

    actions or states of being applied

    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
    StoryboardSegue
    -0.57
     entreten
    -0.50
     jScrollPane
    -0.48
    LOAT
    -0.44
     desarrolla
    -0.44
    +#+#
    -0.43
    ்கு
    -0.43
    ’.”
    -0.43
     bruise
    -0.42
    collate
    -0.42
    POSITIVE LOGITS
     automatically
    0.81
     manually
    0.75
     correctly
    0.73
     explicitly
    0.71
     AssemblyCulture
    0.70
     locally
    0.70
     dynamically
    0.70
     using
    0.67
     inside
    0.66
     asynchronously
    0.66
    Activations Density 1.096%

    No Known Activations