© 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. 14423
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to formal affiliations or associations

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

    "The" followed by abstract nouns

    np_acts-logits-general · gemini-2.0-flash

    the intention or exception

    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
     infatti
    -0.63
    ')):
    -0.58
    ParallelGroup
    -0.56
    WebVitals
    -0.56
    GetBytes
    -0.55
    '},
    -0.54
     gynhyrchwyd
    -0.54
    ']):
    -0.54
    '}>
    -0.54
    QMetaType
    -0.53
    POSITIVE LOGITS
     help
    1.74
     exception
    1.50
     aid
    1.34
    help
    1.31
     aim
    1.23
     assistance
    1.18
     intention
    1.15
     ayuda
    1.11
     intent
    1.08
     caveat
    1.07
    Activations Density 0.210%

    No Known Activations