© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1596
    Prev
    Next
    INDEX
    Explanations

    contextual references to societal issues and human experiences

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

    commonly followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    assisting others

    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
    KommentareTeilen
    -0.90
    DockStyle
    -0.87
     OnInit
    -0.83
    esModule
    -0.82
     يتيمه
    -0.80
     JpaRepository
    -0.78
    TagMode
    -0.77
     للمعارف
    -0.75
    verwijspagina
    -0.74
     onCreateView
    -0.74
    POSITIVE LOGITS
     supporting
    0.76
    Additional
    0.65
     Additional
    0.65
     additional
    0.63
     who
    0.63
     weiteren
    0.63
     assisting
    0.63
     assisted
    0.62
     others
    0.61
    additional
    0.59
    Activations Density 0.215%

    No Known Activations