© 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. 6720
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to the immune system and its functions

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

    "immune" followed by a function/response/system

    np_acts-logits-general · gemini-2.0-flash

    immune system biology

    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
    y
    -0.98
    n
    -0.59
     createState
    -0.57
    <h3>
    -0.55
     Uda
    -0.54
     stor
    -0.54
     Athene
    -0.54
     Lohan
    -0.53
    TIN
    -0.53
    schul
    -0.53
    POSITIVE LOGITS
    venidos
    0.81
    — 
    0.79
    zyż
    0.78
     Catalana
    0.77
    colorPrimary
    0.76
     amarillas
    0.76
    selves
    0.74
     Lesnar
    0.74
     successo
    0.71
     SwitchCompat
    0.71
    Activations Density 0.493%

    No Known Activations