© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    corporate announcements and formal declarations regarding new initiatives or changes

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

    followed by "announced that"

    np_acts-logits-general · gemini-2.0-flash

    announcements of new plans

    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
     HasFactory
    -0.78
    etheless
    -0.74
    woordig
    -0.74
    verwijspagina
    -0.70
     autorytatywna
    -0.69
     estimés
    -0.68
    \{\\
    -0.66
    SOUNDBITE
    -0.66
    Anything
    -0.66
    TypedDataSet
    -0.63
    POSITIVE LOGITS
     plans
    0.69
     new
    0.64
     preliminary
    0.64
     endnu
    0.63
    新たに
    0.63
     oficialmente
    0.62
     further
    0.60
     revised
    0.60
     additional
    0.59
     ANOTHER
    0.59
    Activations Density 0.355%

    No Known Activations