© 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. 18-GEMMASCOPE-RES-16K
    11. 2700
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the purpose or intent of actions

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

    Prepositions before nouns/verbs

    np_acts-logits-general · gemini-2.0-flash

    for the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.70
     Roskov
    -0.60
    XmlAccessorType
    -0.59
     EClass
    -0.55
    iprot
    -0.55
    plotlib
    -0.54
     crossorigin
    -0.54
    زيل
    -0.53
    ɲ
    -0.52
     bø
    -0.52
    POSITIVE LOGITS
     interviews
    0.55
    OLOGÍA
    0.53
     a
    0.51
     extra
    0.50
    phous
    0.49
    schmidt
    0.49
    ITIVE
    0.47
    enance
    0.47
    生平
    0.47
     sheer
    0.47
    Activations Density 0.162%

    No Known Activations