© 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. 6864
    Prev
    Next
    INDEX
    Explanations

    terms related to military hardware, specifically surface-to-air missiles

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

    Follows a determiner or adjective

    np_acts-logits-general · gemini-2.0-flash

    types of military hardware and formal/archaic titles

    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
    esgue
    -0.60
     nau
    -0.42
    createQuery
    -0.41
    naker
    -0.41
    esez
    -0.41
     Nau
    -0.38
     bật
    -0.37
     All
    -0.36
    わ
    -0.36
    !
    -0.36
    POSITIVE LOGITS
     modernisation
    0.81
    ſelf
    0.80
     prototypes
    0.80
     modernized
    0.78
     modernization
    0.77
     Efq
    0.75
     myſelf
    0.75
     Majefty
    0.75
    sidemargin
    0.75
     صوتيه
    0.75
    Activations Density 0.152%

    No Known Activations